Skip to content

Perception Coverage Audit and Backlog

The perception library is broad, but the May 2026 agent sweeps found several method families that are still hidden inside larger documents or missing as first-class pages. Treat this file as the backlog for turning perception research into a method-level library similar to the SLAM coverage audit.

Current Status

ItemStatus
Dedicated perception files38 top-level perception synthesis/audit files, 36 dataset/benchmark pages, and 137 atomic method files plus the method-library overview in Perception Method Library.
Strongest existing coverageProduction sensor suites, CenterPoint/OpenPCDet, BEV basics, method-level camera BEV/occupancy including DepthOcc, sparse-query camera detection, sparse cooperative queries, collaborative Gaussian semantic occupancy, LiDAR-camera occupancy fusion, dynamic occupancy/free-space, spatiotemporal occupancy flow, Gaussian/3DGS/4DGS perception including GS-Occ3D label curation, LiDAR MOS, scene flow, LiDAR artifact removal, learned denoising, adverse-weather datasets, truck-centered V2X datasets, embodied 3D perception benchmarks, FOD synthetic benchmarks and Airport-FOD3S data-engine workflow, motion/static separation benchmarks, aggregated-map semantic segmentation with compact proxy/input/training selection plus companion pages for class taxonomy, training paradigms, tiling/throughput, post-processing, GridNet-HD LiDAR-image utility-infrastructure proxy routing, point-cloud Mamba/SSM backbone routing, LOSC open-vocabulary LiDAR label consolidation, map-hygiene ground-truth workflow routing, static-but-transient point removal, detector-based potentially dynamic object removal, and SLAM map-version-control handoff, radar-camera/radar-LiDAR fusion, 4D radar-camera occupancy, 4D radar road-boundary/freespace detection, radar/event/FMCW, open-world/OOD, open-vocabulary attributes, panoptic/open-vocabulary occupancy, proposal-free open-vocabulary 3D instance segmentation, robust fusion, V2X, latency, data engines, model compression, uncertainty, and thermal fusion.
Most severe structural gapRemaining P0/P1 items still need atomic pages or routing: cooperative semantic-communication and collaborative Gaussian follow-ons beyond VOGS-CP, source-mature LinkOcc or related temporal occupancy follow-ons, occupancy uncertainty/OOD follow-ons beyond the promoted EvOcc page, and public-data gaps for dust, de-icing mist, steam, glycol film, and wet-apron multipath. SAM4D already has an atomic page and should stay routed as a promptable candidate-label/fusion method rather than a missing severe gap. The FOD/adverse-airside proxy boundary is now explicit across dataset, validation, and removal pages; direct airside collection remains the unresolved gap. DR-REMOVER and ExelMap are covered in localization/mapping pages rather than missing perception pages.
How to use this auditUse the method library for promoted atomic pages. Use the P0/P1/P2 rows below as discovery clusters and backlog for remaining splits. Update this audit whenever a missing perception method becomes a dedicated file.

Multi-Agent Discovery Sweep (2026-05-08)

Six parallel research agents audited camera/BEV perception, LiDAR/radar/thermal perception, foundation/open-world perception, temporal tracking, cooperative/V2X perception, and deployment robustness. A second targeted sweep then checked 2025-2026 latest-method and benchmark gaps, followed by lightweight dataset scouts for adverse-weather, event, radar, FMCW LiDAR, V2X, OOD, and latency benchmarks.

Method-Level Promotion Wave (2026-05-08)

Five parallel writing agents converted the highest-value discovery clusters into atomic method pages under methods/. Existing broad perception files should now link into this library rather than expanding into larger catch-all documents.

ClusterPromoted method files
Camera BEV and occupancyBEVDet, BEVDepth, BEVStereo, SOLOFusion, TPVFormer, SurroundOcc, SparseOcc, FlashOcc, SelfOcc, RenderOcc
LiDAR motion, radar, event, and FMCWLiDAR-MOS, 4DMOS, InsMOS, StreamMOS, 4DSegStreamer, SegNet4D, Mask4D, Instantaneous Motion Perception, RadarPillars, K-Radar, V2X-Radar, Ev-3DOD, AevaScenes
Open-world and open-vocabularyOpenAD, OP3Det, WildDet3D, DetAny3D, OW-OVD, Clipomaly, S2M, SAM 3, 3D-AVS, Mosaic3D, SpaCeFormer, OpenVox, LOSC
Robust fusion, calibration, and validationMoME, GraphBEV, SOAC, RC-AutoCalib, ASF, MSC-Bench, MultiCorrupt, S2R-Bench, Occluded nuScenes, Conformal Boxes
Cooperative, latency, closed-loop, and data enginesRCooper, HoloVIC, CoInfra, V2X-ReaLO, CoHFF, CoSDH, CoopTrack, LASP, Fail2Drive, AIDE

Deep-Dive Promotion Wave (2026-05-09)

Fresh parallel discovery and writing agents promoted the first Gaussian/4DGS and latest radar-camera/sparse-query gaps into atomic pages. The rows below are now the primary pages for those methods; older backlog rows remain as provenance for related follow-ons.

ClusterPromoted method files
Gaussian and 3DGS perceptionSplatAD, GaussianFormer, GaussianOcc, Streaming Gaussian Occupancy
4D occupancy and sparse-query perceptionCam4DOcc, StreamingFlow, Sparse4D
Radar-camera fusionTacoDepth, RaCFormer

LIORNet and Adverse-Weather Removal Wave (2026-05-09)

The next loop broadened the LIORNet question from one snow-removal method into a full removal stack: learned LiDAR denoising, classical outlier filters, weather artifact removal, ghost/multipath failure modes, dynamic map cleaning, validation evidence, and weather robustness datasets.

ClusterPromoted files
Learned LiDAR denoising/removalLIORNet, LiSnowNet, SLiDE, TripleMixer, 3D-KNN Blind-Spot Desnowing, 3D-OutDet, AdverseNet, DenoiseCP-Net
Classical and broad artifact removalClassical LiDAR Outlier Removal, LiDAR Weather Artifact Removal, LiDAR Artifact Removal Techniques, LiDAR Ghost and Multipath Artifacts
Weather robustness datasetsWeather Robustness Datasets, WADS, CADC/CADC+, SemanticSTF, REHEARSE-3D, RainSense, SemanticSpray, RADIATE, DSERT-RoLL, CMHT, Seeing Through Fog/DENSE
Safety and map-cleaning bridgeLiDAR Artifact Removal Validation, ERASOR, Removert, LiDAR Map Cleaning and Dynamic Removal

Dynamic/Static Removal and Flow Benchmark Wave (2026-05-09)

The latest loop broadened removal from "delete noisy LiDAR points" into map hygiene: dynamic objects, static objects that do not belong in the persistent map, moved objects, scene flow, moving/static separation, and validation against false deletion.

ClusterPromoted files
MOS and scene-flow methodsMotionSeg3D, MambaMOS, Neural Scene Flow Priors, Scene Flow for Dynamic Object Removal
Motion/static and 4D occupancy benchmarksMoving/Static Separation MOS Datasets, Occupancy-Flow and 4D Occupancy Benchmarks, Scene-Flow Datasets and Benchmarks
Map-cleaning validation bridgeDynamic Map Cleaning Benchmarks, Moved-Object and Map-Change Datasets, Airside Dynamic Map-Cleaning Benchmark

Web Gap Expansion Wave (2026-05-09)

Five web-search scouts and six writing agents promoted a new batch of radar, neural-field, dataset, and validation gaps into first-class pages.

ClusterPromoted files
Radar, 4D radar, and FMCW perceptionCVFusion, 4D Radar-Camera Occupancy, POD FMCW LiDAR Predictive Detection
Dynamic Gaussian, neural-field, and temporal occupancyDrivingGaussian, HUGS, SplatFlow, DistillNeRF, TrackOcc, Cross-Domain LiDAR Scene Flow
World-model bridgeSelf-Supervised Occupancy Flow, UniScene Occupancy-Centric Generation
Datasets and validationMUSES, Sensor Corruption Robustness Benchmarks, Open-World OOD and Anomaly Segmentation Benchmarks, FOD and Airport Apron Detection Datasets, FOD Perception Validation, Knowledge-Base Evaluation Protocol

Reliability and Open-World Gap Wave (2026-05-09)

Six fresh web-search scouts and six writing agents promoted another set of non-duplicate perception gaps into first-class files.

ClusterPromoted files
Occupancy, freespace, and adverse-weather fusionLiDAR-Camera Occupancy Fusion, Dynamic Occupancy and Freespace, Spatiotemporal Memory Occupancy Flow, 4D Radar Road Boundaries and Freespace, Adverse-Weather Radar-LiDAR 3D Detection, RobuRCDet, SAMFusion, GaussianFlowOcc, GaussTR
Open-world and open-vocabulary coverageOVAD/OVODA Open-Vocabulary 3D Attributes, Open-Vocabulary Panoptic Occupancy
Dataset and benchmark coverageSTU 3D LiDAR Anomaly Segmentation, Airside FOD Synthetic Multimodal Benchmarks, RCP-Bench Cooperative Corruption Robustness, V2X Large-Range Sequential Datasets

Recurring Research Loop Promotion (2026-05-22)

Five parallel research scouts checked 2024-2026 perception, localization, dataset, and foundation gaps. The bounded promotion for this loop added one missing camera occupancy method page and kept the rest of the scout findings in the queue.

ClusterPromoted files
Depth-aware camera occupancyDepthOcc
Sparse-query camera detectionSparseBEV, DETR4D
Occupancy follow-onsTEOcc, GaussRender
Adverse-weather multimodal datasetsDSERT-RoLL, CMHT Autonomous Dataset

Recurring Gaussian Occupancy Promotion (2026-05-23)

Five parallel read-only scouts checked the active perception occupancy queue. This bounded pass promoted two source-mature Gaussian occupancy methods and corrected LinkOcc routing so the RobuRCDet arXiv ID is not used as a LinkOcc source.

ClusterPromoted or refreshed coverage
Sparse weakly supervised Gaussian occupancyGaussianFlowOcc
Foundation-model-aligned open-vocabulary Gaussian occupancyGaussTR
Temporal occupancy source hygieneLinkOcc remains a watchlist item with IEEE/DBLP source metadata; do not classify it as radar-camera without primary-source evidence.

Recurring GS-Occ3D Promotion (2026-05-23)

Five parallel read-only scouts checked the perception occupancy queue again. This bounded pass promoted GS-Occ3D as a vision-only Gaussian-surfel occupancy reconstruction and label-curation page, while keeping LinkOcc on watchlist because open method details or code were still not available.

ClusterPromoted or refreshed coverage
Vision-only Gaussian occupancy reconstructionGS-Occ3D
Temporal occupancy source hygieneLinkOcc remains watchlist-only; do not use RobuRCDet's arXiv ID as a LinkOcc source.

Recurring Cooperative Compression Promotion (2026-05-23)

Five read-only scouts checked cooperative compression and quantized V2X perception against existing CoSDH, CoopTrack, V2X-ReaLO, and robust-cooperation coverage. This bounded pass promoted QuantV2X because primary sources provide a paper, project page, official repository, codebook-message design, PTQ workflow, and deployment-oriented latency evidence.

ClusterPromoted or refreshed coverage
Quantized cooperative perceptionQuantV2X

Recurring Sparse Cooperative Query Promotion (2026-05-23)

Five read-only scouts checked the remaining cooperative perception queue after QuantV2X. This bounded pass promoted SparseCoop because the paper is accepted in AAAI 2026, has arXiv and proceedings records, publishes an official MIT-licensed repository, and reports detection, tracking, transmission-cost, and FPS metrics on V2X-Seq and Griffin.

ClusterPromoted or refreshed coverage
Sparse cooperative detection and trackingSparseCoop

Recurring Truck-Centered V2X Dataset Promotion (2026-05-23)

Five read-only scouts checked the remaining cooperative perception queue after SparseCoop. This bounded pass promoted TruckV2X because the dataset has an IEEE RA-L 2025 record, arXiv record, official project page, and Hugging Face dataset release, while CoDS still lacks code/project artifacts and JigsawComm has only a placeholder repository with no released implementation.

ClusterPromoted or refreshed coverage
Truck-centered cooperative perception datasetTruckV2X

Recurring Collaborative Gaussian Occupancy Promotion (2026-05-23)

Five read-only scouts checked the remaining cooperative perception queue after TruckV2X. This bounded pass promoted VOGS-CP because it has an AAAI 2026 proceedings record, arXiv record, official project page, and public repository, and because it cleanly separates collaborative Gaussian semantic occupancy from CoHFF, SparseCoop, and QuantV2X.

ClusterPromoted or refreshed coverage
Collaborative Gaussian semantic occupancyVOGS-CP

Recurring FOD Synthetic Data-Engine Promotion (2026-05-23)

Five read-only scouts checked the FOD/adverse-data queue against existing FOD-A, Airport-FOD3S, RDD5000, weather-proxy, and data-engine coverage. This bounded pass promoted Airport-FOD3S as a focused synthetic FOD data-engine page, added DualFOD/FOD-UAS to the FOD benchmark routing, and added LIDAROC as a LiDAR cover-contamination proxy while keeping airside dust/de-icing/steam/glycol/wet-apron public-data gaps explicit.

ClusterPromoted or refreshed coverage
Synthetic FOD data engineAirport-FOD3S Synthetic FOD Data Engine
FOD multimodal benchmark routingAirside FOD Synthetic and Multimodal Benchmarks now includes DualFOD/FOD-UAS and data-engine cross-links.
Adverse-weather proxy routingWeather Robustness Datasets now routes LIDAROC as a sensor-cover dust/contamination proxy, not a direct jet-blast or de-icing dataset.
FOD proxy-boundary refreshFOD and Airport Apron Detection Datasets, Airside FOD Synthetic and Multimodal Benchmarks, Weather Robustness Datasets, FOD Perception Validation, FOD Retention Map-Cleaning Safety Case, and LiDAR Artifact Removal Techniques now separate public proxy screening from target-airside acceptance evidence and add do-not-delete hazard retention wording.

Recurring Embodied 3D Benchmark Promotion (2026-05-23)

Five read-only scouts checked embodied 3D perception benchmarks, sparse/e2e driving follow-ons, GSCOOP source maturity, active source-registry freshness, and radar/Gaussian SLAM candidates. This bounded pass promoted EmbodiedScan/MMScan as an embodied 3D benchmark page because primary sources provide a CVPR 2024 paper, NeurIPS 2024 Datasets and Benchmarks record, official project pages, a shared official repository, and benchmark tasks.

ClusterPromoted or refreshed coverage
Embodied 3D perception benchmarksEmbodiedScan and MMScan Embodied 3D Benchmarks
Transfer caveatThe new page treats indoor RGB-D and grounded-language benchmarks as spatial-grounding references, not direct outdoor apron safety evidence.

Recurring Open-Vocabulary 3D Segmentation Promotion (2026-05-23)

Five read-only scouts checked DySS, sparse/e2e perception follow-ons, cooperative perception, and indoor open-vocabulary 3D instance segmentation. This bounded pass promoted SpaCeFormer because it has an NVIDIA project page, arXiv record, and released WarpConvNet source, while DySS is already routed through the sparse-query overview and remains code-watch rather than a duplicate atomic page.

ClusterPromoted or refreshed coverage
Proposal-free open-vocabulary 3D instance segmentationSpaCeFormer
Sparse-query routing caveatDySS remains a sparse-query and streaming-temporal overview item until official code or broader adoption justifies a standalone method page.

Recurring Cooperative Source-Hygiene Refresh (2026-05-23)

Five read-only scouts checked cooperative/infrastructure source drift after CoInfra, HoloVIC, and V2X-ReaLO had already been promoted. This bounded maintenance pass corrected CoInfra from the RCooper arXiv ID to 2507.02245, corrected V2X-ReaLO from an unrelated arXiv ID to 2503.10034, corrected HoloVIC CVF links to the Ma_HoloVIC CVPR 2024 record, and refreshed routing for V2XScenes, UrbanIng-V2X, V2XPnP, and CoopScenes in the infrastructure-cooperative and large-range dataset pages.

Recurring Point-Cloud SSM Backbone Promotion (2026-05-23)

Five read-only scouts checked the aggregated-map segmentation queue after the Uni-Mapper pass. This bounded pass promoted point-cloud Mamba/SSM backbones as one method-family page rather than separate immature pages per variant, because the family is relevant to map-scale token cost but still lacks production map-release evidence.

ClusterPromoted or refreshed coverage
Point-cloud Mamba / SSM segmentation backbonesPoint-Cloud Mamba / SSM Backbones
Aggregated-map routingAggregated-Map Semantic Segmentation, LiDAR Semantic Segmentation, and Large-Scale 3D Segmentation Tiling and Throughput now treat SSMs as a research-stage efficiency branch, not a P1 production default.

Recurring Aggregated-Map Architecture Routing (2026-05-24)

This bounded pass kept existing method pages as the atomic deep dives and added an architecture reading path in the method library, because the aggregated-map hub already compares the families but readers still needed a product-oriented route across the individual method pages.

ClusterRefreshed coverage
Method-library routingPerception Method Library Overview now groups aggregated-map segmentation methods into sparse-voxel production anchors, point-conv geometry baselines, superpoint graph map-scale context, serialized transformer/foundation-model ceilings, projection and standard-op deployment lanes, image-distilled/open-vocabulary label lanes, and SSM/Mamba experiments.
Bake-off controlsThe method-library route now requires shared source-map acceptance packages, taxonomy, release-state labels, tile manifests, halo policy, optimizer budget, modality lanes, and semantic plus hygiene metrics before claiming one architecture beats another.

Recurring LOSC Consolidation Promotion (2026-05-23)

Five read-only scouts checked LOSC source maturity, page schema, cross-links, count updates, and active queue priority. This bounded pass promoted LOSC as an atomic method page because the arXiv, OpenReview, Valeo project page, and official repository are public, while existing repo coverage only mentioned it inside overview/data-engine paragraphs.

ClusterPromoted or refreshed coverage
Open-vocabulary LiDAR pseudo-label consolidationLOSC
Aggregated-map routingAggregated-map segmentation, open-vocabulary detection, data-engine, active-labeling, and annotation-tool pages now treat LOSC outputs as candidate or pseudo-labeled regions until reviewer, taxonomy, QA, manifest, and map-hygiene gates promote them.

Recurring Map-Hygiene Workflow Refresh (2026-05-23)

Five read-only scouts checked the active aggregated-map segmentation queue and found that the map-hygiene ground-truth protocol had two useful but weakly connected owners: a canonical map-operations protocol and a safety-validation companion. This bounded pass kept both pages, made the ownership boundary explicit, and routed the protocol through semantic-map QA, publication gates, operational monitoring, regulatory evidence, README, INDEX, and the active loop queue.

ClusterRefreshed coverage
Map-hygiene protocol ownershipAirside Map Hygiene Ground Truth Protocol now owns layer labels, capture slices, reviewer dispositions, QA gates, and benchmark splits.
V&V workflow handoffAirside Map Hygiene Ground Truth Protocol now acts as the benchmark and acceptance-output companion instead of an ambiguous duplicate.
Aggregated-map routingAggregated-map segmentation, map construction, publication gates, monitoring, and regulatory evidence now share the same static/movable/dynamic/FOD/artifact/unknown vocabulary.

Recurring Aggregated-Map Selector Refresh (2026-05-23)

Five read-only scouts checked the compact selector candidate against existing dataset/proxy, training-paradigm, LOSC, UniLiPs, and map-hygiene coverage. This bounded pass kept the content in the aggregated-map hub instead of creating a new page, because the repo already has detailed companion pages for datasets, training paradigms, tiling, post-processing, and static-transient removal.

ClusterRefreshed coverage
Compact selectorAggregated-Map Semantic Segmentation now includes a compact proxy/input/training selector for airside, dense urban districts, non-road sites, calibrated camera+LiDAR surveys, existing SLAM maps, long corridors, and mesh/digital-twin release.
Training companion routing3D Segmentation Training Paradigms now points readers to the hub selector for operational routing while keeping the detailed training trade-offs in one place.

Recurring BeautyMap Dynamic-Removal Promotion (2026-05-23)

Five read-only scouts checked the aggregated-map segmentation and pointcloud-removal queue. This bounded pass promoted BeautyMap as the binary-encoded ground-matrix cleaner because it is official-code-backed, KTH-benchmark-routed, and directly supports the dynamic-removal conditioning stage before map-scale semantic segmentation.

Next perception promotion queue: LinkOcc remains a watchlist item until open method details or code make an atomic page reviewable. Other remaining items are e2e sparse-query perception follow-ons where they need separate pages, cooperative follow-ons such as CoDS, JigsawComm, GSCOOP-style collaborative Gaussian BEV segmentation, and airside-specific dust/de-icing/steam/glycol/wet-apron validation datasets. SparseDriveV2 and DiffusionDriveV2 are now routed through planning/E2E benchmark refreshes rather than new perception pages; DySS is routed through sparse-query and streaming-temporal overviews pending official code/adoption. DSERT-RoLL and CMHT are promoted as public multimodal adverse-weather dataset proxies, TruckV2X is promoted as a truck-centered V2X proxy, VOGS-CP is promoted as the collaborative Gaussian semantic-occupancy reference, EmbodiedScan/MMScan is promoted as the embodied 3D benchmark reference, SpaCeFormer is promoted as the proposal-free open-vocabulary 3D instance segmentation reference, LOSC is promoted as the open-vocabulary LiDAR pseudo-label consolidation reference, and Airport-FOD3S is promoted as the synthetic FOD data-engine reference, but no public dataset found in this loop directly covers airside dust, de-icing mist, steam, glycol film, or wet-apron multipath. Missing-view occupancy routes through M2-Occ, temporal radar-camera occupancy routes through TEOcc, Gaussian-rendered occupancy routes through GaussRender, and vision-only Gaussian occupancy label curation routes through GS-Occ3D unless a distinct method needs its own file.

Suggested fileMethod or techniqueCategoryWhy it mattersPrimary sources
camera-bev-depth-aware-encoders.mdBEVDet, BEVDepth, BEVStereo, BEVPoolv2, BEVDet4D, SOLOFusionDepth-aware camera BEVThe current BEV doc jumps from LSS to BEVFormer; depth-supervised LSS-family encoders are more practical for LiDAR-supervised airside camera fallback.https://arxiv.org/abs/2206.10092, https://arxiv.org/abs/2209.10248, https://arxiv.org/abs/2203.17054, https://openreview.net/forum?id=H3HcEJA2Um
camera-only-3d-occupancy.mdTPVFormer, SurroundOcc, Occ3D/OpenOcc, FB-OCC, FlashOcc, SparseOcc, SelfOcc, RenderOccCamera semantic occupancyCamera occupancy is now a core planning-facing alternative to boxes for arbitrary shapes, FOD, personnel, and unknown obstacles.https://openaccess.thecvf.com/content/CVPR2023/html/Huang_Tri-Perspective_View_for_Vision-Based_3D_Semantic_Occupancy_Prediction_CVPR_2023_paper.html, https://openaccess.thecvf.com/content/ICCV2023/html/Wei_SurroundOcc_Multi-camera_3D_Occupancy_Prediction_for_Autonomous_Driving_ICCV_2023_paper.html, https://arxiv.org/abs/2304.14365, https://openaccess.thecvf.com/content/CVPR2024/html/Tang_SparseOcc_Rethinking_Sparse_Latent_Representation_for_Vision-Based_Semantic_Occupancy_Prediction_CVPR_2024_paper.html
lidar-moving-object-segmentation.mdLiDAR-MOS, 4DMOS, InsMOS, MF-MOS, MV-MOS/CV-MOS, SegNet4D, Mask4D, HeLiMOSMoving-object segmentation and 4D panoptic LiDARAirside needs point-level static/dynamic separation for parked-vs-moving GSE, map cleanup, track birth, and prediction gating.https://arxiv.org/abs/2105.08971, https://arxiv.org/abs/2206.04129, https://arxiv.org/abs/2401.17023, https://arxiv.org/abs/2408.10602, https://arxiv.org/abs/2406.16279, https://github.com/url-kaist/HeLiMOS-PointCloud-Toolbox
streaming-mos-4d-panoptic.mdStreamMOS and 4DSegStreamerStreaming temporal segmentationAdds memory across inferences, not only within one scan window; useful for high-FPS streams and occlusion consistency.https://arxiv.org/abs/2407.17905, https://llada60.github.io/4DSegStreamer/
Promoted: Instantaneous Motion PerceptionInstantaneous perception of moving objects in 3DSubtle motion estimationAirside has creeping tugs and quasi-static objects; this fills the gap between single-frame detection and track-derived velocity.https://openaccess.thecvf.com/content/CVPR2024/html/Liu_Instantaneous_Perception_of_Moving_Objects_in_3D_CVPR_2024_paper.html, https://arxiv.org/abs/2405.02781
4d-occupancy-forecasting.mdCam4DOcc, StreamingFlow, UnO, DFIT-OccWorld, Drive-OccWorldPerception-to-prediction handoffTracks alone cannot represent unknown, partially observed, or occluded movers; 4D occupancy/flow is a stronger planner interface.https://openaccess.thecvf.com/content/CVPR2024/html/Ma_Cam4DOcc_Benchmark_for_Camera-Only_4D_Occupancy_Forecasting_in_Autonomous_Driving_CVPR_2024_paper.html, https://openaccess.thecvf.com/content/CVPR2024/html/Shi_StreamingFlow_Streaming_Occupancy_Forecasting_with_Asynchronous_Multi-modal_Data_Streams_via_CVPR_2024_paper.html, https://openaccess.thecvf.com/content/CVPR2024/html/Agro_UnO_Unsupervised_Occupancy_Fields_for_Perception_and_Forecasting_CVPR_2024_paper.html, https://arxiv.org/abs/2412.13772
4d-radar-perception-methods.mdK-Radar, View of Delft, RadarPillars, V2X-Radar4D radar perceptionRadar is covered mainly as hardware/fusion; the perception stack needs tensor-vs-point representations, Doppler/RCS encoding, and benchmark limits.https://github.com/kaist-avelab/K-Radar, https://intelligent-vehicles.org/datasets/view-of-delft/, https://arxiv.org/abs/2408.05020, https://arxiv.org/abs/2411.10962
multi-sensor-corruption-benchmarks.mdMSC-Bench and MultiCorruptRobustness and corruption evaluationAdds systematic camera+LiDAR corruptions, missing inputs, misalignment, temporal mismatch, adverse weather, and sensor failures.https://arxiv.org/abs/2501.01037, https://arxiv.org/abs/2402.11677, https://github.com/ika-rwth-aachen/MultiCorrupt
real-sensor-anomaly-robustness.mdS2R-Bench and Occluded nuScenesReal sensor anomaly and occlusion validationAdds real adverse-weather/sensor-anomaly data and parameterized camera/radar/LiDAR occlusion tests beyond synthetic corruption overlays.https://www.nature.com/articles/s41597-025-06255-3, https://arxiv.org/abs/2505.18631, https://arxiv.org/abs/2510.18552
open-world-ood-perception-benchmarks.mdOpenAD and S2M OOD object segmentationOpen-world/OOD evaluationCurrent docs cover generic OOD scores; these add benchmarkable 3D corner cases and mask-level unknown-object localization.https://arxiv.org/abs/2411.17761, https://github.com/VDIGPKU/OpenAD, https://openaccess.thecvf.com/content/CVPR2024/html/Zhao_Segment_Every_Out-of-Distribution_Object_CVPR_2024_paper.html
open-world-open-vocab-detection.mdOW-OVDOpen-world plus open-vocabulary 2D detectionExisting open-vocab coverage emphasizes prompted known classes; OW-OVD adds unknown-object recall and incremental learning.https://openaccess.thecvf.com/content/CVPR2025/html/Xi_OW-OVD_Unified_Open_World_and_Open_Vocabulary_Object_Detection_CVPR_2025_paper.html
open-world-3d-objectness.mdOpenAD, OP3Det, WildDet3D, DetAny3DPrompt-free and promptable 3D objectnessFills the gap between closed-set 3D detection, text-prompted 3D detection, and true unknown-object discovery in 3D.https://openreview.net/forum?id=T9UDyN5Tw6, https://arxiv.org/abs/2411.17761, https://openreview.net/forum?id=wEOmS8Aw1W, https://arxiv.org/abs/2510.17686, https://arxiv.org/abs/2604.08626, https://openaccess.thecvf.com/content/ICCV2025/papers/Zhang_Detect_Anything_3D_in_the_Wild_ICCV_2025_paper.pdf
open-world-anomaly-segmentation-driving.mdClipomaly, S2M, SegmentMeIfYouCanUnknown-region and anomaly segmentationDedicated anomaly stack for OOD masks, RoadObstacle/RoadAnomaly metrics, and airside FOD adaptation.https://arxiv.org/abs/2512.01427, https://arxiv.org/abs/2311.16516, https://segmentmeifyoucan.com/
sam3-concept-segmentation-airside.mdSAM 3 / SAM 3.1 concept segmentation and trackingFoundation-model auto-labelingCurrent docs stop at SAM/SAM2/Grounded-SAM2; SAM 3 adds open-vocabulary concept prompts, exemplars, and video tracking for GSE/FOD labeling.https://arxiv.org/abs/2511.16719, https://github.com/facebookresearch/sam3
resilient-fusion-sensor-failure.mdMoME / nuScenes-R failure routingRobust fusion under sensor failureDirectly handles LiDAR drop, camera drop, limited FOV, beam reduction, and occlusion as perception architecture, not only robustness theory.https://openaccess.thecvf.com/content/CVPR2025/html/Park_Resilient_Sensor_Fusion_Under_Adverse_Sensor_Failures_via_Multi-Modal_Expert_CVPR_2025_paper.html, https://github.com/konyul/MoME
robust-fusion-asynchrony-calibration.mdStaleness-aware fusion, GraphBEV, SOAC, RC-AutoCalibTemporal sync and calibration driftCovers silent fusion failure from stale sensors, extrinsic drift, LiDAR-camera misalignment, radar-camera calibration, and asynchronous inputs.https://arxiv.org/abs/2506.05780, https://arxiv.org/abs/2403.11848, https://github.com/adept-thu/GraphBEV, https://openaccess.thecvf.com/content/CVPR2024/html/Herau_SOAC_Spatio-Temporal_Overlap-Aware_Multi-Sensor_Calibration_using_Neural_Radiance_Fields_CVPR_2024_paper.html, https://openaccess.thecvf.com/content/CVPR2025/html/Luu_RC-AutoCalib_An_End-to-End_Radar-Camera_Automatic_Calibration_Network_CVPR_2025_paper.html
roadside-infrastructure-cooperative-datasets.mdRCooper and HoloVICRoadside/infrastructure cooperative perception datasetsAdds real multi-RSPU and multi-layout infrastructure perception, closer to airport fixed-sensor coverage than V2V-only datasets.https://openaccess.thecvf.com/content/CVPR2024/html/Hao_RCooper_A_Real-world_Large-scale_Dataset_for_Roadside_Cooperative_Perception_CVPR_2024_paper.html, https://github.com/AIR-THU/DAIR-RCooper, https://openaccess.thecvf.com/content/CVPR2024/html/Ma_HoloVIC_Large-scale_Dataset_and_Benchmark_for_Multi-Sensor_Holographic_Intersection_and_CVPR_2024_paper.html, https://arxiv.org/abs/2403.02640
infrastructure-adverse-weather-cooperative-perception.mdCoInfraMulti-node infrastructure plus adverse weatherStrong airport analogue: synchronized infrastructure nodes, real weather, 5G delay-aware fusion, OTA, monitoring, and system docs.https://arxiv.org/abs/2507.02245, https://github.com/NingMingHao/CoInfra
v2x-online-realtime-benchmarks.mdV2X-ReaLOOnline V2X framework and datasetExisting docs are mostly offline-benchmark oriented; this targets synchronized ROS bags, latency, and online intermediate fusion.https://arxiv.org/abs/2503.10034
cooperative-occupancy-perception.mdCoHFF collaborative semantic occupancyCooperative occupancyFills a major gap: dense 3D semantic occupancy, not only boxes, for irregular cargo, unknown obstacles, and FOD.https://openaccess.thecvf.com/content/CVPR2024/html/Song_Collaborative_Semantic_Occupancy_Prediction_with_Hybrid_Feature_Fusion_in_Connected_CVPR_2024_paper.html, https://github.com/rruisong/CoHFF
communication-efficient-cooperative-fusion.mdCoSDHBandwidth-efficient hybrid fusionSupply-demand region selection plus intermediate/late hybridization is more deployment-oriented than pure intermediate fusion.https://openaccess.thecvf.com/content/CVPR2025/html/Xu_CoSDH_Communication-Efficient_Collaborative_Perception_via_Supply-Demand_Awareness_and_Intermediate-Late_Hybridization_CVPR_2025_paper.html
cooperative-sequential-tracking.mdCoopTrackCooperative MOT and sequential perceptionExisting cooperative docs emphasize detection; airport planners need stable IDs and motion continuity across agents.https://openaccess.thecvf.com/content/ICCV2025/html/Zhong_CoopTrack_Exploring_End-to-End_Learning_for_Efficient_Cooperative_Sequential_Perception_ICCV_2025_paper.html, https://arxiv.org/abs/2507.19239
uncertainty-detection-conformal-abstention.mdConformal bounding boxes and conformal abstentionDetection-specific uncertaintyUpgrades conformal coverage from class sets to localization intervals and explicit abstain/degrade decisions.https://arxiv.org/abs/2403.07263, https://arxiv.org/abs/2502.07255
Promoted: AIDEAIDE automatic data engineLong-tail detection data engineConcrete loop for issue mining, auto-labeling, scenario generation, and open-world detection evaluation.https://openaccess.thecvf.com/content/CVPR2024/html/Liang_AIDE_An_Automatic_Data_Engine_for_Object_Detection_in_Autonomous_CVPR_2024_paper.html, https://arxiv.org/abs/2403.17373
30-autonomy-stack/perception/methods/vespa-open-world-pointcloud-labeling.mdVESPA and adjacent VLM-assisted 3D auto-labelingOpen-world point-cloud labelingMultimodal pseudo-labeling without GT annotations or HD maps directly addresses airside 3D labeling bottlenecks; the ScienceDirect source is an adjacent VLM/pseudo-LiDAR auto-annotation reference, not a VESPA source.https://arxiv.org/abs/2507.20397, https://www.sciencedirect.com/science/article/pii/S0968090X25004334

P1 Remaining Atomic Pages or Major Sections

Suggested fileMethod or techniqueCategoryWhy it mattersPrimary sources
camera-panoptic-open-vocab-occupancy.mdPanoOcc, VEON, LangOcc, OpenOccCamera panoptic/open-vocabulary occupancyAdds instance-level and open-vocabulary 3D scene understanding for rare GSE, barriers, FOD, and long-tail objects.https://openaccess.thecvf.com/content/CVPR2024/html/Wang_PanoOcc_Unified_Occupancy_Representation_for_Camera-based_3D_Panoptic_Segmentation_CVPR_2024_paper.html, https://arxiv.org/abs/2407.12294, https://openreview.net/forum?id=KhjlXNbYea, https://github.com/boschresearch/LangOcc, https://arxiv.org/abs/2403.11796
camera-4d-occupancy-forecasting.mdCam4DOcc, OccProphet, ALOccTemporal camera occupancyCurrent temporal perception coverage is stronger on detection/tracking than camera 4D occupancy.https://openaccess.thecvf.com/content/CVPR2024/html/Ma_Cam4DOcc_Benchmark_for_Camera-Only_4D_Occupancy_Forecasting_in_Autonomous_Driving_CVPR_2024_paper.html, https://openreview.net/forum?id=vC7AlY1ytz, https://huggingface.co/papers/2411.07725
Promoted: Streaming Gaussian OccupancyGaussianWorld and S2GOStreaming Gaussian occupancyMoves from per-frame occupancy toward persistent sparse Gaussian/query world state for real-time temporal occupancy.https://openaccess.thecvf.com/content/CVPR2025/html/Zuo_GaussianWorld_Gaussian_World_Model_for_Streaming_3D_Occupancy_Prediction_CVPR_2025_paper.html, https://openreview.net/forum?id=z8ggdMlSco, https://arxiv.org/abs/2506.05473
generalized-uncalibrated-occupancy.mdOccAny and ViGTGeneralized / calibration-free occupancyTargets uncalibrated, out-of-domain, monocular, sequential, and surround-view occupancy for heterogeneous camera rigs.https://arxiv.org/abs/2603.23502, https://github.com/valeoai/OccAny, https://arxiv.org/abs/2602.05573
missing-view-resilient-occupancy.mdM2-OccIncomplete multi-camera robustnessDirectly tests missing camera/view dropout for semantic occupancy.https://arxiv.org/abs/2603.09737
occupancy-uncertainty-ood-evidence.mdProOOD follow-on; EvOcc is promotedOccupancy uncertainty / OODHandles unknown objects, occluded voxels, contradictory evidence, and long-tail classes at occupancy level without duplicating the existing EvOcc page.https://openaccess.thecvf.com/content/CVPR2025/html/Kalble_EvOcc_Accurate_Semantic_Occupancy_for_Automated_Driving_Using_Evidence_Theory_CVPR_2025_paper.html, https://arxiv.org/abs/2604.01081
satellite-assisted-occupancy.mdSA-OccSatellite / overhead-map assisted occupancyEspecially relevant to airside because overhead imagery and GPS/IMU can reduce occlusion and distant-region weakness.https://openaccess.thecvf.com/content/ICCV2025/html/Chen_SA-Occ_Satellite-Assisted_3D_Occupancy_Prediction_in_Real_World_ICCV_2025_paper.html
Promoted: Spatiotemporal Memory Occupancy FlowST-Occ and STCOccTemporal occupancy and scene flowAdds memory, uncertainty-aware aggregation, sparse state refinement, and scene-flow prediction as a planner-facing interface.https://openaccess.thecvf.com/content/ICCV2025/html/Leng_Occupancy_Learning_with_Spatiotemporal_Memory_ICCV_2025_paper.html, https://openaccess.thecvf.com/content/CVPR2025/html/Liao_STCOcc_Sparse_Spatial-Temporal_Cascade_Renovation_for_3D_Occupancy_and_Scene_CVPR_2025_paper.html
Promoted: Sparse Query Camera 3D Detection, SparseBEV, DETR4D, Sparse4DSparse4D, SparseBEV, DETR4D, object-query temporal memorySparse multi-view camera detectionFocused taxonomy and atomic method pages for sparse query methods versus dense BEV methods for edge deployment.https://arxiv.org/abs/2211.10581, https://arxiv.org/abs/2308.09244, https://arxiv.org/abs/2212.07849, https://arxiv.org/abs/2602.00450
camera-depth-stereo-foundation-models.mdDepth Pro, Video Depth Anything, FoundationStereoCamera depth and stereo foundation modelsUpdates fallback perception beyond Depth Anything v2, Metric3D, and UniDepth with metric, temporal, and zero-shot stereo options.https://arxiv.org/abs/2410.02073, https://arxiv.org/abs/2501.12375, https://github.com/DepthAnything/Video-Depth-Anything, https://arxiv.org/abs/2501.09898, https://research.nvidia.com/labs/lpr/publication/stereoanything2025/
camera-lidar-fusion-interfaces.mdFUTR3D, CMT, DeepInteraction, AutoAlignV2, DAL, SAMFusion, MS-OccCamera-LiDAR fusion interfacesExisting docs cover BEVFusion but underrepresent query fusion, calibration-tolerant alignment, dynamic modality dropout, and occupancy fusion.https://arxiv.org/abs/2203.10642, https://arxiv.org/abs/2301.01283, https://proceedings.neurips.cc/paper_files/paper/2022/hash/0d18ab3b5fabfa6fe47c62e711af02f0-Abstract-Conference.html, https://arxiv.org/abs/2207.10316, https://arxiv.org/abs/2311.07152, https://arxiv.org/abs/2508.16408, https://arxiv.org/abs/2504.15888
camera-bev-robustness-validation.mdRoboBEV, BEV corruptions, viewpoint robustness, missing camera inputs, occupancy uncertaintyCamera BEV validationAirside camera rigs, soiling, glare, missing cameras, and calibration changes need benchmark coverage.https://arxiv.org/abs/2304.06719, https://arxiv.org/abs/2405.17426, https://arxiv.org/abs/2309.05192, https://arxiv.org/abs/2406.11021, https://arxiv.org/abs/2603.09737
adverse-weather-radar-lidar-3d-detection.mdLiDAR-4D radar fusion, L4DR, V2X-RRadar-LiDAR adverse-weather detectionDirectly addresses when radar should rescue LiDAR detection under fog/rain.https://openaccess.thecvf.com/content/CVPR2024/papers/Chae_Towards_Robust_3D_Object_Detection_with_LiDAR_and_4D_Radar_CVPR_2024_paper.pdf, https://arxiv.org/abs/2408.03677, https://openaccess.thecvf.com/content/CVPR2025/papers/Huang_V2X-R_Cooperative_LiDAR-4D_Radar_Fusion_with_Denoising_Diffusion_for_3D_CVPR_2025_paper.pdf
Promoted: DepthOccDepthOccDepth-aware camera occupancyReal-time camera semantic occupancy using monocular/stereo depth fusion and temporal enhancement; keep separate from radar-camera queues unless a method adds radar inputs.https://doi.org/10.1016/j.cviu.2026.104670, https://tsinghua-mars-lab.github.io/Occ3D/
LinkOcc routing/watchlistLinkOcc temporal-association occupancy plus separate radar-camera follow-onsTemporal occupancy and source hygieneLinkOcc is IEEE TCSVT 2025 "3D Semantic Occupancy Prediction With Temporal Association"; do not cite RobuRCDet's arXiv ID as LinkOcc or classify LinkOcc as radar-camera without primary-source evidence.https://ieeexplore.ieee.org/document/10734407, https://dblp.org/rec/journals/tcsv/OuyangXSWX25.html, https://arxiv.org/abs/2502.13071
Promoted: 4D Radar-Camera Occupancy4DRC-OCC and RadarOccRadar-camera semantic occupancyDense occupancy using 4D radar plus camera is distinct from LiDAR-camera occupancy and generic dynamic occupancy; keep this row as provenance and watch radar-occupancy follow-ons.https://arxiv.org/abs/2603.07794
Promoted: Availability-Aware Sensor FusionAvailability-aware Sensor Fusion via Unified Canonical SpaceSensor-failure perceptionDirectly targets missing/degraded camera, LiDAR, and 4D radar availability instead of assuming all modalities are valid.https://arxiv.org/abs/2503.07029
event-camera-3d-detection.mdEv-3DOD / DSEC-3DOD and eAPEvent-camera 3D perceptionEvent cameras now support 3D detection and time-to-collision, not just 2D detection or VIO.https://arxiv.org/abs/2502.19630, https://openaccess.thecvf.com/content/CVPR2025/papers/Cho_Ev-3DOD_Pushing_the_Temporal_Boundaries_of_3D_Object_Detection_with_CVPR_2025_paper.pdf, https://arxiv.org/abs/2603.16303
fmcw-lidar-perception.mdAevaScenes and POD predictive object detectionFMCW / 4D LiDAR perceptionPer-point velocity changes detection, scene-flow, and predictive-detection design compared with pulsed LiDAR.https://www.aeva.com/press/aeva-introduces-aevascenes-the-first-open-access-fmcw-4d-lidar-and-camera-dataset-for-autonomous-vehicle-research/, https://arxiv.org/abs/2504.05649
Promoted: 4D Radar Road Boundaries and Freespace4DRadarRBDRadar freespace and road-boundary detectionRadar-based boundary/freespace perception is separate from object detection and occupancy, especially in poor visibility.https://arxiv.org/abs/2503.01930, https://www.frontiersin.org/articles/10.3389/frsip.2025.1667789/
fully-sparse-lidar-detectors.mdVoxelNeXt, DSVT, fully sparse detector upgrade pathLiDAR 3D detectionopenpcdet-centerpoint.md is CenterPoint-heavy; modern candidates should include sparse detectors with better dense-BEV cost profiles.https://github.com/open-mmlab/OpenPCDet, https://arxiv.org/abs/2303.11301, https://arxiv.org/abs/2301.06051
thermal-lidar-dense-perception.mdThermal-LiDAR depth completion, RGB-T-LiDAR segmentation, dense night freespaceThermal/night dense perceptionCurrent thermal doc is detection/safety-use-case oriented; dense depth and segmentation matter for freespace and occupancy.https://arxiv.org/abs/2504.02356, https://doi.org/10.1016/j.isprsjprs.2026.01.008, https://oem.flir.com/en-gb/solutions/automotive/adas-dataset-form/, https://soonminhwang.github.io/rgbt-ped-detection/, https://github.com/bupt-ai-cz/LLVIP
Promoted: Dynamic Occupancy and FreespaceDIO, MS-Occ, UniOccCurrent-state occupancy and freespacePerception docs need the current-state safety view that planners consume, distinct from predictive world models.https://openaccess.thecvf.com/content/CVPR2025/papers/Diehl_DIO_Decomposable_Implicit_4D_Occupancy-Flow_World_Model_CVPR_2025_paper.pdf, https://arxiv.org/abs/2504.15888, https://arxiv.org/abs/2503.24381
Promoted: LiDAR-Camera Occupancy FusionSDG-OCC and MS-OccLiDAR-camera occupancy fusionOccupancy-specific fusion uses LiDAR geometry plus camera semantics through depth guidance, distillation, and multi-stage fusion.https://openaccess.thecvf.com/content/CVPR2025/html/Duan_SDGOCC_Semantic_and_Depth-Guided_Birds-Eye_View_Transformation_for_3D_Multimodal_CVPR_2025_paper.html, https://arxiv.org/abs/2504.15888
uncertainty-aware-bev-fusion.mdGaussianLSS and HyperDUMFusion-specific uncertaintyAdds BEV depth uncertainty and low-cost feature-level multimodal uncertainty closer to deployed fusion stacks.https://openaccess.thecvf.com/content/CVPR2025/html/Lu_Toward_Real-world_BEV_Perception_Depth_Uncertainty_Estimation_via_Gaussian_Splatting_CVPR_2025_paper.html, https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Hyperdimensional_Uncertainty_Quantification_for_Multimodal_Uncertainty_Fusion_in_Autonomous_Vehicles_CVPR_2025_paper.html
night-thermal-event-radar-benchmarks.mdNSAVP and V2X-RadarNight, thermal, event, radar evaluationUpdates night perception beyond FLIR/KAIST-style references with stereo thermal, event cameras, 4D radar, rain/night/dusk cooperative data.https://umautobots.github.io/nsavp, https://arxiv.org/abs/2401.13853, https://arxiv.org/abs/2411.10962
edge-real-time-bev-scheduling.mdRT-BEV and JigsawDeadline-aware BEV deploymentCompression doc is TensorRT-heavy; add P99/WCET scheduling and dual-SoC partitioning.https://rtcl.eecs.umich.edu/rtclweb/assets/publications/2024/rtss24-liu.pdf, https://2024.rtss.org/accepted-papers/index.html, https://dblp.org/rec/conf/rtss/SunLHHX0BSRG24.html
40-runtime-systems/ros-autoware/sensor-in-memory-ros2-av-middleware.mdSIM shared-memory transport for ROS 2 / AutowareDeployment latency and middlewareTargets perception-to-decision tail latency, not only model inference time.https://arxiv.org/abs/2510.11448
ood-data-engine.mdDriveGEN and active OOD generationActive data and evaluationComplements uncertainty-triggered logging with controllable OOD augmentation and scenario generation.https://openaccess.thecvf.com/content/CVPR2025/html/Lin_DriveGEN_Generalized_and_Robust_3D_Detection_in_Driving_via_Controllable_CVPR_2025_paper.html
uncertainty-aware-end-to-end-3d-mot.mdS2-TrackTracking uncertaintyQuery initialization, probabilistic decoder, and uncertainty as downstream prediction signal are currently underdocumented.https://proceedings.mlr.press/v267/tang25p.html, https://openreview.net/forum?id=vHr9cdeFfu, https://arxiv.org/abs/2406.02147
relation-aware-3d-mot.mdGRAE-3DMOTRelation-aware trackingComplements MCTrack/3DMOTFormer with relation-aware association for dense scenes.https://openaccess.thecvf.com/content/CVPR2025/html/Kim_GRAE-3DMOT_Geometry_Relation-Aware_Encoder_for_Online_3D_Multi-Object_Tracking_CVPR_2025_paper.html
latency-aware-streaming-perception.mdLASP online benchmark, Transtreaming, multi-modal streaming 3D detectionLatency compensation and online evaluationSeparate acquisition latency, inference latency, output timestamp compensation, and time-stale quality on edge hardware.https://arxiv.org/abs/2504.19115, https://arxiv.org/abs/2409.06584, https://arxiv.org/abs/2209.04966
4d-world-model-pretraining.mdDriveWorldTemporal representation pretrainingConcrete 4D pretraining bridge across detection, tracking, forecasting, occupancy, and planning.https://arxiv.org/abs/2405.04390, https://openaccess.thecvf.com/content/CVPR2024/html/Min_DriveWorld_4D_Pre-trained_Scene_Understanding_via_World_Models_for_Autonomous_CVPR_2024_paper.html
object-query-cooperative-perception.mdCoopDETRSparse cooperative communicationObject-query sharing is interpretable and extremely bandwidth-light versus region/BEV maps.https://arxiv.org/abs/2502.19313
collaboration-robust-cooperative-fusion.mdmmCooperRobust multi-stage fusionTargets bandwidth limits plus calibration/misalignment errors in cooperative perception.https://openaccess.thecvf.com/content/ICCV2025/html/Liu_mmCooper_A_Multi-agent_Multi-stage_Communication-efficient_and_Collaboration-robust_Cooperative_Perception_Framework_ICCV_2025_paper.html
spatiotemporal-cooperative-perception.mdCoSTSpace-time cooperative fusionUnifies multi-agent and temporal fusion; avoids retransmitting static-object features repeatedly.https://openaccess.thecvf.com/content/ICCV2025/html/Tang_CoST_Efficient_Collaborative_Perception_From_Unified_Spatiotemporal_Perspective_ICCV_2025_paper.html
end-to-end-v2x-cooperative-driving.mdV2Xverse / CoDriving, UniV2X, Select2DriveClosed-loop V2X perception-to-planningMoves evaluation from mAP-only to driving score, collision rate, latency, and communication-aware planning.https://collaborativeperception.github.io/V2Xverse/, https://github.com/CollaborativePerception/V2Xverse, https://arxiv.org/abs/2404.00717
privacy-adaptation-v2x-collaboration.mdUnknown-collaborator privacy and CoPEFTPrivacy/domain adaptationCovers separately trained agents, privacy-preserving fusion, and low-cost per-site adaptation for multi-vendor fleets.https://mlanthology.org/aaai/2025/lu2025aaai-privacy/, https://ojs.aaai.org/index.php/AAAI/article/view/34502
auto-vocabulary-lidar-segmentation.md3D-AVSLiDAR open-vocabulary segmentationDistinguishes LiDAR foundation pretraining from runtime vocabulary discovery for point clouds.https://openaccess.thecvf.com/content/CVPR2025/html/Wei_3D-AVS_LiDAR-based_3D_Auto-Vocabulary_Segmentation_CVPR_2025_paper.html, https://arxiv.org/abs/2406.09126
mosaic3d-open-vocab-3d-segmentation.mdMosaic3DOpen-vocabulary 3D segmentationFoundation dataset/model for open-vocabulary 3D semantic and instance segmentation; fills a gap beyond 2D open-vocabulary segmentation.https://research.nvidia.com/labs/lpr/publication/choy2025mosaic/, https://openaccess.thecvf.com/content/CVPR2025/papers/Lee_Mosaic3D_Foundation_Dataset_and_Model_for_Open-Vocabulary_3D_Segmentation_CVPR_2025_paper.pdf
openvox-open-vocab-voxel-mapping.mdOpenVoxOpen-vocabulary voxel mappingReal-time instance-level probabilistic voxel memory is relevant for persistent apron maps and language-queryable scene memory.https://open-vox.github.io/
ago-open-world-3d-occupancy.mdAGO adaptive groundingOpen-world 3D occupancyKnown/unknown semantic occupancy using VLM grounding is a stronger safety-layer fit than box-only open-world detection.https://arxiv.org/abs/2504.10117, https://openaccess.thecvf.com/content/ICCV2025/papers/Li_AGO_Adaptive_Grounding_for_Open_World_3D_Occupancy_Prediction_ICCV_2025_paper.pdf
Promoted: Open3DTrackOpen3DTrackOpen-vocabulary 3D trackingFirst-pass gaps covered 3D detection/objectness but not persistent open-vocabulary 3D tracks.https://arxiv.org/abs/2410.01678
open-vocab-monocular-3d-detection.mdOVM3D-DetOpen-vocab monocular 3D detectionUseful as offline/assistive camera fallback, with safety caveats.https://ovm3d-det.github.io/, https://arxiv.org/abs/2411.15657
dense-open-vocab-segmentation.mdFlorence-2, CAT-Seg, ProxyCLIP, AutoSeg/AVSDense open-vocabulary labelsGrounded-SAM is not the whole dense-labeling story; pixel-level OV segmentation helps mask QA and rare-class discovery.https://arxiv.org/abs/2311.06242, https://huggingface.co/microsoft/Florence-2-large, https://openaccess.thecvf.com/content/CVPR2024/html/Cho_CAT-Seg_Cost_Aggregation_for_Open-Vocabulary_Semantic_Segmentation_CVPR_2024_paper.html, https://arxiv.org/abs/2408.04883, https://openaccess.thecvf.com/content/ICCV2025/html/Ulger_Auto-Vocabulary_Semantic_Segmentation_ICCV_2025_paper.html
ovad-open-vocab-3d-attributes.mdOVAD / OVODAOpen-vocabulary 3D attributesAdds attribute-level open-vocabulary 3D detection, which matters for airside state labels such as cones, tugs, carts, lights, covers, and unusual vehicle configurations.https://arxiv.org/abs/2508.16812
Covered: VLM/VLA Reliability BenchmarksDriveBenchVLM driving reliability under corruptionsTests clean, corrupted, and text-only driving QA to catch visually ungrounded VLM perception or monitoring outputs. Keep as a cross-link, not a duplicate method page.https://drive-bench.github.io/, https://github.com/worldbench/DriveBench
airside-fod-open-world-benchmarks.mdFOD-A, FAA FOD framing, Airport-FOD3S, RDD5000, DualFOD/FOD-UASResidual airside FOD OOD benchmark planFOD-A, Airport-FOD3S, RDD5000, and DualFOD/FOD-UAS are now routed or promoted; the residual gap is a dedicated benchmark plan for tiny-object recall, OOD-vs-detector comparison, and public airside dust/de-icing/steam/glycol/wet-apron negatives.https://arxiv.org/abs/2110.03072, https://github.com/FOD-UNOmaha/FOD-data, https://www.faa.gov/airports/airport_safety/fod, https://www.mdpi.com/1424-8220/25/15/4565, https://www.mdpi.com/2072-4292/17/4/669, https://www.mdpi.com/2504-446X/10/3/225
Promoted: Airport-FOD3S Synthetic FOD Data EngineAirport-FOD3SSynthetic FOD data engineSynthetic FOD generation and blending directly addresses rare small-object data scarcity beyond FOD-A, with data-lineage and real-only validation gates.https://www.mdpi.com/1424-8220/25/15/4565
Promoted: Fail2DriveFail2DriveClosed-loop OOD validationPaired-route distribution-shift scenarios expose perception-linked failures under closed-loop drift.https://arxiv.org/abs/2604.08535, https://github.com/autonomousvision/fail2drive

P2 or Watchlist

Method or techniqueWhy watchCurrent concernSources
VLMFusionOcc3D, OccVLA, O3NVLM-assisted and open-vocabulary occupancy are moving quickly.Promising but not yet safety perception primitives; validate hallucination, latency, and reproducibility.https://arxiv.org/abs/2603.02609, https://huggingface.co/papers/2509.05578, https://arxiv.org/abs/2603.12144
RayD3D, Dr.Occ, SuperOcc, Gau-OccUseful 2025-2026 camera/multimodal/Gaussian occupancy signals.Mostly preprint-stage or narrow-benchmark. GaussRender, GaussianFlowOcc, GaussTR, and GS-Occ3D are promoted as method pages.https://huggingface.co/papers/2603.22852, https://arxiv.org/abs/2603.01007, https://openaccess.thecvf.com/content/CVPR2025/html/Oh_3D_Occupancy_Prediction_with_Low-Resolution_Queries_via_Prototype-aware_View_Transformation_CVPR_2025_paper.html, https://gs-occ3d.github.io/
EventFly, EvDET200K, TUMTraf EMOT, PRE-MambaEvent perception is expanding into dense segmentation, high-definition detection, MOT, and rain removal.Useful follow-ons for event-camera pages; promote after dataset/code adoption and hardware fit are clearer.https://openaccess.thecvf.com/content/CVPR2025/html/Kong_EventFly_Event_Camera_Perception_from_Ground_to_the_Sky_CVPR_2025_paper.html, https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Object_Detection_using_Event_Camera_A_MoE_Heat_Conduction_based_CVPR_2025_paper.html, https://arxiv.org/abs/2512.14595, https://arxiv.org/abs/2505.05307
DSERT-RoLLStereo event/RGB/thermal, 4D radar, and dual-LiDAR dataset for diverse driving conditions.Promoted into DSERT-RoLL; keep watching for benchmark/code updates and license changes.https://arxiv.org/abs/2604.03685
HyperDet, DRIFT, SD4R, R4Det2026 radar-only/radar-camera perception line.Needs code, repeatable benchmarks, and multi-dataset validation.https://arxiv.org/abs/2602.11554, https://arxiv.org/abs/2603.09695, https://arxiv.org/abs/2602.20653, https://arxiv.org/abs/2603.11566
SiMO and single-modality-operable cooperative perceptionDirectly relevant to robust collaborative perception under sensor failures.Too fresh; compare against MoME, HEAL, mmCooper, and CoSDH before promotion.https://gist.science/paper/2603.08240
CoDS, JigsawComm, and GSCOOP2025-2026 cooperative perception wave around semantic communication, compression, utility scheduling, and sparse Gaussian sharing.Useful but not yet mature enough for core docs; CoDS still lacks code/project/final-venue artifacts, JigsawComm has only a placeholder repository, and GSCOOP's official repo link is currently 404/private despite public ICCV paper/poster sources. Compare against CoSDH, mmCooper, CoST, V2X-ReaLO, promoted VOGS-CP, promoted TruckV2X, promoted SparseCoop, and promoted QuantV2X first.https://arxiv.org/abs/2512.22513, https://arxiv.org/abs/2511.17843, https://github.com/WiSeR-Lab/JigsawComm, https://openaccess.thecvf.com/content/ICCV2025/html/Hong_Communication-Efficient_Multi-Vehicle_Collaborative_Semantic_Segmentation_via_Sparse_3D_Gaussian_Sharing_ICCV_2025_paper.html
LightDiff and JarvisIRRestoration can help low-light/weather preprocessing.Treat as monitored advisory preprocessing, not safety authority, because restoration can hallucinate.https://openaccess.thecvf.com/content/CVPR2024/html/Li_Light_the_Night_A_Multi-Condition_Diffusion_Framework_for_Unpaired_Low-Light_CVPR_2024_paper.html, https://openaccess.thecvf.com/content/CVPR2025/html/Lin_JarvisIR_Elevating_Autonomous_Driving_Perception_with_Intelligent_Image_Restoration_CVPR_2025_paper.html
T-Rex2 and OWLv2 visual-prompt detectionVisual exemplars help airport-specific GSE variants where text prompts are brittle.Better for onboarding and annotation acceleration than runtime safety perception.https://arxiv.org/abs/2403.14610, https://github.com/IDEA-Research/T-Rex, https://arxiv.org/abs/2306.09683
DySS, GaussianDet3D, OffsetOcc, Diffusion-FSUseful follow-ons for streaming camera detection, Gaussian camera detection, panoptic completion, and corridor prediction.DySS is routed through existing sparse-query and streaming-temporal overviews until official code or broader adoption justifies an atomic page. The others remain useful research directions, but merge into existing occupancy, SAM/data-engine, or freespace pages unless adoption grows. ForeSight and SAM4D already have atomic pages.https://arxiv.org/abs/2506.10242, https://openaccess.thecvf.com/content/CVPR2025W/WAD/html/Yasarla_DySS_Dynamic_Queries_and_State-Space_Learning_for_Efficient_3D_Object_CVPRW_2025_paper.html, https://openreview.net/forum?id=qByiOX1j9C, https://cvpr.thecvf.com/virtual/2025/35771, https://arxiv.org/abs/2507.18763

Benchmark and Dataset Gaps

Dataset or benchmarkWhy it should be addedSources
OpenADReal open-world autonomous-driving benchmark for 3D object detection across corner cases and unseen categories.https://openreview.net/forum?id=T9UDyN5Tw6, https://arxiv.org/abs/2411.17761, https://github.com/VDIGPKU/OpenAD
OVAD / OVODAOpen-vocabulary multimodal 3D detection plus attribute labels for long-tail object state reasoning.https://arxiv.org/abs/2508.16812
DriveBenchCovered in VLM/VLA Reliability Benchmarks; keep cross-linked for perception reliability rather than duplicating a method page.https://drive-bench.github.io/, https://github.com/worldbench/DriveBench
Promoted: EmbodiedScan and MMScan Embodied 3D BenchmarksEgocentric RGB-D 3D perception, semantic occupancy, visual grounding, and 3D QA benchmark coverage for spatial VLM/VLA evaluation.https://tai-wang.github.io/embodiedscan/, https://openaccess.thecvf.com/content/CVPR2024/html/Wang_EmbodiedScan_A_Holistic_Multi-Modal_3D_Perception_Suite_Towards_Embodied_AI_CVPR_2024_paper.html, https://tai-wang.github.io/mmscan/, https://proceedings.neurips.cc/paper_files/paper/2024/hash/5aed0d900297bd5593afc14ff452d4a8-Abstract-Datasets_and_Benchmarks_Track.html
FOD-A and FAA FOD guidancePromoted into FOD and Airport Apron Detection Datasets and FOD Perception Validation; keep extending with wet/dark splits, OOD handling, and operational hazard severity.https://arxiv.org/abs/2110.03072, https://github.com/FOD-UNOmaha/FOD-data, https://www.faa.gov/airports/airport_safety/fod
Airport-FOD3S, RDD5000, DualFOD / FOD-UASSynthetic FOD generation, RGB/IR runway detection, and synchronized RGB/thermal FOD imagery are now listed in the FOD dataset page with explicit proxy-boundary language; Airport-FOD3S is also promoted as a synthetic data-engine workflow.https://www.mdpi.com/1424-8220/25/15/4565, https://www.mdpi.com/2072-4292/17/4/669, https://www.mdpi.com/2504-446X/10/3/225
RCooper and HoloVICFixed infrastructure, multi-RSPU, and holographic intersection perception datasets useful for airport stand/terminal layouts.https://openaccess.thecvf.com/content/CVPR2024/html/Hao_RCooper_A_Real-world_Large-scale_Dataset_for_Roadside_Cooperative_Perception_CVPR_2024_paper.html, https://openaccess.thecvf.com/content/CVPR2024/html/Ma_HoloVIC_Large-scale_Dataset_and_Benchmark_for_Multi-Sensor_Holographic_Intersection_and_CVPR_2024_paper.html
V2X-Real, TUMTraf-V2X, V2X-ReaLO, V2XScenes, UrbanIng-V2X, CoInfraReal V2X, online realism, detection/tracking, large-range V2I, multi-intersection generalization, weather, 5G delay, and infrastructure fusion.https://github.com/ucla-mobility/V2X-Real, https://arxiv.org/abs/2403.16034, https://tum-traffic-dataset.github.io/tumtraf-v2x/, https://arxiv.org/abs/2403.01316, https://arxiv.org/abs/2503.10034, https://openaccess.thecvf.com/content/ICCV2025/html/Wang_V2XScenes_A_Multiple_Challenging_Traffic_Conditions_Dataset_for_Large-Range_Vehicle-Infrastructure_ICCV_2025_paper.html, https://arxiv.org/abs/2510.23478, https://arxiv.org/abs/2507.02245
V2X-RadarCooperative 4D radar plus camera/LiDAR for rainy, night, and dusk scenarios.https://openreview.net/forum?id=sTKsFIVqik, https://arxiv.org/abs/2411.10962, https://github.com/yanglei18/V2X-Radar, https://huggingface.co/datasets/yanglei18/V2X-Radar
NSAVPNight stereo-thermal/event-style adverse-visibility benchmark support.https://umautobots.github.io/nsavp, https://arxiv.org/abs/2401.13853
DSEC-3DOD, CoSEC, eTraM, EvTTC, SEVD, SPECTRAEvent-camera 3D detection, event-frame alignment, traffic detection, TTC, synthetic event data, and dense real driving labels.https://arxiv.org/abs/2502.19630, https://arxiv.org/abs/2408.08500, https://eventbasedvision.github.io/eTraM/, https://arxiv.org/abs/2403.19976, https://nail-hnu.github.io/EvTTC/, https://github.com/eventbasedvision/SEVD, https://openreview.net/forum?id=mqCUxEsfsI
AevaScenesFMCW 4D LiDAR plus camera dataset; per-point velocity changes detection, scene-flow, and predictive-perception evaluation.https://scenes.aeva.com, https://www.aeva.com/press/aeva-introduces-aevascenes-the-first-open-access-fmcw-4d-lidar-and-camera-dataset-for-autonomous-vehicle-research/, https://github.com/aevainc
L-RadSetLong-range camera, LiDAR, and 4D-radar dataset with annotated long-range radar targets.https://ieeexplore.ieee.org/document/10591452/, https://github.com/crrasjtu/L-RadSet
RainSense and REHEARSE-3DNatural rain intensity labels plus point-cloud deraining support for LiDAR/radar adverse-weather perception.https://saemobilus.sae.org/papers/rainsense-autonomous-driving-environmental-perception-dataset-rain-intensity-annotations-2025-01-7311, https://arxiv.org/abs/2504.21699
Promoted: CMHT Autonomous DatasetRadar, infrared, LiDAR, and camera ROS 2 data for rain/night multimodal perception.https://www.sciencedirect.com/science/article/pii/S2352340925002847
Promoted: DSERT-RoLLBroad multimodal driving dataset with stereo event, RGB, thermal, 4D radar, and dual LiDAR.https://jeongyh98.github.io/dsert-roll/, https://huggingface.co/datasets/jeongyh98/DSERT-RoLL, https://arxiv.org/abs/2604.03685
K-Radar and View of DelftCore 4D radar perception benchmarks for radar-native detection and fusion.https://github.com/kaist-avelab/K-Radar, https://intelligent-vehicles.org/datasets/view-of-delft/
Dual Radar, Boreas-RT, HeRCULES, SNAIL RadarRadar/FMCW LiDAR bridge datasets for detection, tracking, odometry, place recognition, and heavy-rain/night stress testing.https://www.nature.com/articles/s41597-025-04698-2, https://github.com/adept-thu/Dual-Radar, https://www.boreas.utias.utoronto.ca, https://arxiv.org/abs/2602.16870, https://sites.google.com/view/herculesdataset, https://arxiv.org/abs/2502.01946, https://snail-radar.github.io/
IDD-AW, RASMD, TWICERGB/NIR/SWIR and digital-twin adverse-weather datasets for rain, fog, snow, glare, low light, and controlled HIL testing.https://iddaw.github.io/, https://arxiv.org/abs/2504.07603, https://twicedataset.github.io/site/
R-LiViT, RTPSeg, Pi3DETThermal/LiDAR roadside VRU, RGB-thermal LiDAR segmentation, and cross-platform 3D detection generalization remain follow-ons after the semantic-map dataset refresh.https://openaccess.thecvf.com/content/ICCV2025/html/Mirlach_R-LiViT_A_LiDAR-Visual-Thermal_Dataset_Enabling_Vulnerable_Road_User_Focused_Roadside_ICCV_2025_paper.html, https://arxiv.org/abs/2503.17122, https://github.com/sssssyf/RTPSeg, https://pi3det.github.io/
Promoted: SemanticTHAB, WHU-Urban3D, CUS3D, SUM PartsRouted into Large-Scale 3D Point Cloud Semantic Segmentation Benchmarks and Aggregated-Map Semantic Segmentation as high-resolution MLS, mixed MLS/ALS urban, photogrammetric point/mesh/image, and part-level urban mesh proxies for the end-to-end aggregated-map pipeline.https://zenodo.org/records/14906179, https://github.com/kav-institute/SemanticLiDAR, https://whu3d.com/dataset/, https://whu3d.com/benchmark.html, https://www.mdpi.com/2072-4292/16/6/1079, https://arxiv.org/abs/2503.15300, https://tudelft3d.github.io/SUMParts/
Promoted: GridNet-HDAdded as a LiDAR-image utility-infrastructure benchmark for long-thin pylon, cable, insulator, vegetation, soil/road, water, and building classes; routed into the large-scale benchmark page, aggregated-map selector, and taxonomy caution layer rather than treated as direct airside evidence.https://arxiv.org/abs/2601.13052, https://huggingface.co/datasets/heig-vd-geo/GridNet-HD, https://huggingface.co/collections/heig-vd-geo/gridnet-hd
Routed: ECLAIR, YUTO Semantic, S.MID, OpenTrench3D, MLDAS, USCILab3D, Industrial3DRouted through Large-Scale 3D Point Cloud Semantic Segmentation Benchmarks, Aggregated-Map Semantic Segmentation, and 3D Segmentation Class Taxonomy Design as aerial/site-survey, campus, industrial/substation, utility-trench, cross-LiDAR, long-term campus, and dense TLS industrial proxies. No atomic dataset pages yet; Industrial3D and USCILab3D remain release-maturity watch items, MLDAS is email-gated/non-commercial, and OpenTrench3D is photogrammetric rather than LiDAR.https://github.com/SharperShape/eclair-dataset, https://huggingface.co/datasets/ausmlab/yuto-semantic, https://github.com/Cavendish518/SFPNet, https://github.com/SimonBuusJensen/OpenTrench3D, https://sychen320.github.io/projects/MLDAS/, https://proceedings.neurips.cc/paper_files/paper/2024/hash/628433f240414517fd95164b4275f5cc-Abstract-Datasets_and_Benchmarks_Track.html, https://github.com/pointcloudyc/Industrial3D
Routed: Point Cloud City / Open3D-ML PCC and City-FacadeRouted through Large-Scale 3D Point Cloud Semantic Segmentation Benchmarks, Aggregated-Map Semantic Segmentation, and 3D Segmentation Class Taxonomy Design as managed-building/public-safety and MLS facade/vertical-structure proxies. They improve terminal-interior, terminal-frontage, label-unification, small safety-feature, and digital-twin taxonomy coverage, but neither is direct airside acceptance evidence.https://www.nist.gov/services-resources/software/point-cloud-city-open3d-ml-repository, https://www.nist.gov/publications/cross-dataset-semantic-segmentation-performance-analysis-unifying-nist-point-cloud-city, https://github.com/alexdimopoulos/PointCloudCity-Open3D-ML, https://doi.org/10.1016/j.isprsjprs.2026.01.003, https://github.com/SYSU-3DSTAILab/City-Facade
Routed: ZAHARouted through the large-scale benchmark page, aggregated-map segmentation hub, and taxonomy design page as the current largest public MLS facade-hierarchy benchmark. ZAHA adds 601 M annotated points, 66 facades, and LoFG2/LoFG3 class hierarchy for terminal-frontage, vertical-structure, and digital-twin taxonomy stress, but it is not a full-site road/yard/apron validation dataset or a dynamic-removal source.https://openaccess.thecvf.com/content/WACV2025/html/Wysocki_ZAHA_Introducing_the_Level_of_Facade_Generalization_and_the_Large-Scale_WACV_2025_paper.html, https://github.com/OloOcki/zaha, https://tum2t.win/datasets/pc-mls, https://tum2t.win/benchmarks/pc-fac
LiDARWeather, SemanticSTF, Robo3D, RADIATEWeather and corruption benchmarks for LiDAR segmentation/detection and radar-heavy adverse-weather perception.https://arxiv.org/abs/2407.02286, https://github.com/engineerJPark/LiDARWeather, https://github.com/xiaoaoran/SemanticSTF, https://arxiv.org/abs/2303.17597, https://pro.hw.ac.uk/radiate/
MSC-Bench and MultiCorruptMulti-sensor corruptions, missing modalities, misalignment, temporal mismatch, and sensor failures.https://arxiv.org/abs/2501.01037, https://arxiv.org/abs/2402.11677
MapBenchCamera/LiDAR corruption benchmark for HD map construction robustness, complementary to object-detection corruption suites.https://mapbench.github.io/
S2R-Bench and Occluded nuScenesReal sensor anomaly, adverse weather, and parameterized sensor occlusion tests for camera/radar/LiDAR fusion.https://www.nature.com/articles/s41597-025-06255-3, https://arxiv.org/abs/2505.18631, https://arxiv.org/abs/2510.18552
RCP-BenchCooperative-perception corruption benchmark covering ego/CAV/infrastructure degradation and temporal misalignment.https://openaccess.thecvf.com/content/CVPR2025/papers/Du_RCP-Bench_Benchmarking_Robustness_for_Collaborative_Perception_Under_Diverse_Corruptions_CVPR_2025_paper.pdf, https://github.com/LuckyDush/RCP-Bench
LASP online benchmark and PLM-NetLatency-aware streaming perception and control-delay evaluation for time-stale 3D detection quality and vision-based AV control under delay.https://arxiv.org/abs/2504.19115, https://awskhalil.github.io/plm-net/, https://arxiv.org/abs/2407.16740
Fail2DriveClosed-loop paired-route benchmark for distribution-shift failures that can expose perception-linked compounding errors.https://arxiv.org/abs/2604.08535, https://github.com/autonomousvision/fail2drive
SegmentMeIfYouCan / RoadObstacle / RoadAnomalyOOD segmentation and unknown obstacle evaluation for camera-side anomaly detection.https://segmentmeifyoucan.com/
HeLiMOSHeterogeneous LiDAR moving-object segmentation benchmark/tooling.https://github.com/url-kaist/HeLiMOS-PointCloud-Toolbox
Occ3D, OpenOccupancy, OpenScene, Cam4DOcc, UniOcc, nuCraft, CarlaOcc / ADMeshOccupancy prediction, high-resolution occupancy, panoptic synthetic occupancy, and forecasting benchmarks that should be cross-linked from perception, not only world models.https://arxiv.org/abs/2304.14365, https://github.com/OpenDriveLab/OpenScene, https://openaccess.thecvf.com/content/CVPR2024/html/Ma_Cam4DOcc_Benchmark_for_Camera-Only_4D_Occupancy_Forecasting_in_Autonomous_Driving_CVPR_2024_paper.html, https://uniocc.github.io/, https://arxiv.org/abs/2503.24381, https://benjin.me/publication/eccv2024_nucraft/, https://arxiv.org/abs/2603.27238, https://mias.group/CarlaOcc
Promoted: EmbodiedScan and MMScan Embodied 3D BenchmarksIndoor embodied 3D perception, visual grounding, and QA benchmarks useful as spatial-grounding references.https://tai-wang.github.io/embodiedscan/, https://openaccess.thecvf.com/content/CVPR2024/html/Wang_EmbodiedScan_A_Holistic_Multi-Modal_3D_Perception_Suite_Towards_Embodied_AI_CVPR_2024_paper.html, https://tai-wang.github.io/mmscan/, https://openreview.net/forum?id=z1nITsHKb4

Already Covered, But Needs Better Discoverability

Existing fileAdd aliases or cross-links for
BEV Encoding ArchitecturesBEVDet, BEVDepth, BEVStereo, BEVPoolv2, BEVDet4D, SOLOFusion, DuoSpaceNet, DenseBEV, SEPatch3D.
Camera-Only Degraded PerceptionDepth Pro, Video Depth Anything, FoundationStereo, OVM3D-Det, camera occupancy fallback, MultiCorrupt/MSC-Bench degradation tests.
Open-Vocabulary and Zero-Shot DetectionSplit open-vocabulary known-class detection from open-world unknown-object discovery; add OW-OVD, SAM 3, OP3Det, 3D-AVS, Clipomaly, S2M, T-Rex2.
Vision Foundation ModelsFlorence-2, CAT-Seg, ProxyCLIP, AutoSeg/AVS, SAM 3, data-engine use cases, and OOD segmentation.
LiDAR Foundation Models3D-AVS, OpenAD, OP3Det, open-world objectness, and auto-vocabulary point-cloud segmentation.
LiDAR Semantic SegmentationLiDAR-MOS, 4DMOS, MotionSeg3D, MambaMOS, SegNet4D, Mask4D, ALPINE, HeLiMOS, moving/static labels, scene-flow signals, and 4D panoptic outputs.
OpenPCDet and CenterPointVoxelNeXt, DSVT, fully sparse detectors, RadarPillars, and camera-LiDAR/radar fusion interfaces.
Streaming Temporal PerceptionStreamMOS, 4DSegStreamer, MotionSeg3D, MambaMOS, Neural Scene Flow Priors, Cam4DOcc, UnO, DFIT-OccWorld, Drive-OccWorld, LASP, Transtreaming, acquisition-vs-inference latency.
Multi-Object TrackingS2-Track, GRAE-3DMOT, CoopTrack, uncertainty/existence output contracts, occlusion age, source modality, track history quality.
Infrastructure Cooperative PerceptionRCooper, HoloVIC, CoInfra, V2X-ReaLO, QuantV2X, TruckV2X, VOGS-CP, V2XScenes, UrbanIng-V2X, V2X-Radar, online realism and latency traces.
Collaborative Fleet PerceptionCoSDH, SparseCoop, QuantV2X, VOGS-CP, mmCooper, CoST, CoopDETR, CoopTrack, CoHFF, V2Xverse, privacy/adaptation for unknown collaborators.
Uncertainty QuantificationConformal boxes, conformal abstention, GaussianLSS, HyperDUM, segmentation/occupancy/freespace uncertainty, modality health.
Model Compression and Edge DeploymentQuantV2X, RT-BEV, Jigsaw, P99/WCET gates, multi-model contention, compression-vs-robustness regression checks.
Night Operations and Thermal FusionNSAVP, V2X-Radar, thermal-LiDAR dense perception, event cameras, thermal calibration drift, hot-engine clutter, rain-on-lens.
Production Perception SystemsProduction validation matrix: missing modality, stale modality, miscalibration, sensor occlusion, darkness, fog/rain, degraded compute.
Data Flywheel, Data Engines, and Airport-FOD3S Synthetic FOD Data EngineAIDE, SAM 3, Florence-2, OOD triggers, cooperative metadata, FOD-specific QA gates, synthetic sample lineage, and real-only holdout rules.

Guardrail Process

When adding or revising perception research:

  1. Check whether the method is already a dedicated file, an existing section, or a backlog item in this audit.
  2. If it is P0, create one atomic file under 30-autonomy-stack/perception/methods/ before expanding lower-priority coverage.
  3. If it is P1, either create one atomic method file or add aliases and cross-links from the closest existing method page.
  4. If it is P2/watchlist, add aliases only after primary sources, code, or dataset availability are confirmed.
  5. Keep family synthesis in top-level perception docs and detailed method evidence in methods/.
  6. After every perception expansion, update this audit, Research Index, README, and any related safety/data-engine docs.

Public research notes collected from public sources.