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
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 .
Forward citations
Cited by 25 Pith papers
-
FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction
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.
-
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
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.
-
RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection
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.
-
Kerr-Schild Double Copy of the Randall-Sundrum Black String
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.
-
TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
TaCarla releases 2.85M CARLA Leaderboard 2.0 frames with nuScenes-style sensors, multi-task annotations, planning baselines, and a text-based rarity score.
-
Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking
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.
-
Semantic Causality-Aware Vision-Based 3D Occupancy Prediction
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%.
-
Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection
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 ...
-
BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning
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.
-
CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
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.
-
MambaMap: Online Vectorized HD Map Construction using State Space Model
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.
-
SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction
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.
-
Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline
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.
-
OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception
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.
-
Coherent Online Road Topology Estimation and Reasoning with Standard-Definition Maps
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...
-
S2GO: Streaming Sparse Gaussian Occupancy Prediction
A sparse-query, streaming Gaussian occupancy predictor achieves state-of-the-art 3D semantic occupancy on nuScenes and KITTI with real-time inference.
-
SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation
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.
-
Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey
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...
-
Occupancy Learning with Spatiotemporal Memory
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...
-
Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification
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.
-
Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy
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.
-
GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction
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.
-
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
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.
-
OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving
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.
-
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
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.
Discussion (0). Sign in to comment.