Pith. sign in

REVIEW 25 cited by

BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.17054 v3 pith:LD6PNGFR submitted 2022-03-31 cs.CV

classification cs.CV
keywords bevdet4dbevdetframeperformancecuesdetectiondubbedmulti-camera
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms. For fundamentally pushing the performance boundary in this area, a novel paradigm dubbed BEVDet4D is proposed to lift the scalable BEVDet paradigm from the spatial-only 3D space to the spatial-temporal 4D space. We upgrade the naive BEVDet framework with a few modifications just for fusing the feature from the previous frame with the corresponding one in the current frame. In this way, with negligible additional computing budget, we enable BEVDet4D to access the temporal cues by querying and comparing the two candidate features. Beyond this, we simplify the task of velocity prediction by removing the factors of ego-motion and time in the learning target. As a result, BEVDet4D with robust generalization performance reduces the velocity error by up to -62.9%. This makes the vision-based methods, for the first time, become comparable with those relied on LiDAR or radar in this aspect. On challenge benchmark nuScenes, we report a new record of 54.5% NDS with the high-performance configuration dubbed BEVDet4D-Base, which surpasses the previous leading method BEVDet-Base by +7.3% NDS. The source code is publicly available for further research at https://github.com/HuangJunJie2017/BEVDet .

Discussion (0). Sign in to comment.

Forward citations

Cited by 25 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Factorized Dense Routing approximates unconstrained 2D-to-3D feature mixing by hierarchical tensor contractions, yielding global-context occupancy prediction that remains robust without camera extrinsics.

  2. MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Block-wise Modal Joint Attention over image, LiDAR, and diffusion action tokens yields 88.9 PDMS / 88.4 EPDMS on NAVSIM without anchors or auxiliary supervision.

  3. RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    RECO adds learnable near/far 6-DoF pose corrections to roadside BEV detectors, smoothly blended by a sigmoid gate, improving 3D detection under camera extrinsic jitter and drift.

  4. Kerr-Schild Double Copy of the Randall-Sundrum Black String

    hep-th 2026-04 unverdicted novelty 6.0 of 10

    Kerr-Schild double copy of the RS II black string produces a sourceless Maxwell single copy and a warp-induced massive scalar zeroth copy, with an alternative splitting giving inequivalent gauge and scalar fields.

  5. TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving

    cs.RO 2026-02 conditional novelty 6.0 of 10

    TaCarla releases 2.85M CARLA Leaderboard 2.0 frames with nuScenes-style sensors, multi-task annotations, planning baselines, and a text-based rarity score.

  6. Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Latent Gaussian Splatting (LaGS) replaces dense voxel feature encoders with sparse feature-bearing Gaussians and achieves state-of-the-art 4D panoptic occupancy tracking on nuScenes and Waymo.

  7. Semantic Causality-Aware Vision-Based 3D Occupancy Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.

  8. Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection

    cs.CV 2025-08 conditional novelty 6.0 of 10

    AdaBEV improves low-resolution BEV detection for multi-UAV scenes by refining object-centered grids and adding instance-background contrastive learning, reaching 0.783 AP vs 0.759 for BEVFormer at 50x50 resolution on ...

  9. BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A contrastive learning framework with instance-level and perspective-level losses consistently improves multiple BEV detection models on nuScenes by up to 2.4 mAP.

  10. CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CoST unifies multi-agent and multi-time fusion into a single spatio-temporal space and transmits only dynamic object features, improving collaborative 3D detection accuracy while reducing bandwidth.

  11. MambaMap: Online Vectorized HD Map Construction using State Space Model

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MambaMap fuses four previous frames of BEV features and instance queries via gated state space layers, beating prior HD map construction methods on nuScenes and Argoverse2.

  12. SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SDGOCC improves multimodal 3D occupancy prediction by using LiDAR depth and semantic masks to guide camera-to-BEV transformation, achieving state-of-the-art mIoU on Occ3D-nuScenes.

  13. Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline

    cs.CV 2025-07 conditional novelty 6.0 of 10

    S3AD decouples 2D and 3D supervision and adds a disparity-only foreground head with RbAF scoring, detecting out-of-distribution 3D objects from stereo images, validated on the new KITTI-AR dataset.

  14. OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception

    cs.CV 2025-07 conditional novelty 6.0 of 10

    OnlineBEV achieves state-of-the-art 3D object detection on nuScenes by recurrently fusing bird's eye view features with motion-guided deformable attention and a heatmap consistency loss.

  15. Coherent Online Road Topology Estimation and Reasoning with Standard-Definition Maps

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Score jointly detects lane segments, road boundaries, and traffic elements, estimates lane topology, and associates traffic elements with lanes, using SD map priors and temporal fusion to reach state-of-the-art on Ope...

  16. S2GO: Streaming Sparse Gaussian Occupancy Prediction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A sparse-query, streaming Gaussian occupancy predictor achieves state-of-the-art 3D semantic occupancy on nuScenes and KITTI with real-time inference.

  17. SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    SliceSemOcc improves 3D semantic occupancy prediction by slicing voxel features into global and local height bands and applying per-height channel attention, yielding modest mIoU gains on nuScenes benchmarks.

  18. Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey

    cs.RO 2025-08 conditional novelty 5.0 of 10

    A safety-critical survey that organizes BEV perception into single-modality, multimodal, and collaborative stages and consolidates robustness evidence that multimodal fusion degrades far less than single-modality perc...

  19. Occupancy Learning with Spatiotemporal Memory

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    ST-Occ improves 3D occupancy prediction for self-driving by storing a compact scene-level memory of past frames and conditioning current predictions on it with uncertainty-aware attention, gaining 3 mIoU over prior st...

  20. Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification

    cs.RO 2025-08 unverdicted novelty 5.0 of 10

    Estimating robot dynamics parameters from trajectory data alone inside a differentiable simulator, inside the reinforcement learning loop, is claimed to improve trajectory following in bipedal locomotion.

  21. Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy

    cs.CV 2025-07 reject novelty 5.0 of 10

    A multi-task camera model that adds local-density-aware occupancy prediction to 3D object detection reports strong nuScenes scores, but internal inconsistencies and missing code prevent confirmation.

  22. GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GTAD combines an in-model latent denoising network with global temporal interaction to improve camera-based 3D semantic occupancy prediction, reporting 40.76 mIoU on Occ3D-nuScenes at 12 epochs.

  23. Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots

    cs.RO 2025-07 conditional novelty 5.0 of 10

    A humanoid-specific multimodal occupancy perception system with a new dataset, sensor layout, and a fusion network that claims state-of-the-art results on its own benchmark.

  24. OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Adding object-centric radiance-field rendering and height-aware opacity attention to the DualBEV detector improves camera-only 3D object detection on nuScenes by up to 2.0 mAP points.

  25. DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos

    cs.CV 2025-06 conditional novelty 5.0 of 10

    DySS combines state-space feature learning with dynamic query merging and pruning to improve both accuracy and speed for camera-based 3D detection on nuScenes.

Pith tools