Papers › BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

21 Jun 2022arXiv:2206.10092archive 2025-07-28

Yinhao Li, Zheng Ge, Guanyi Yu, Jinrong Yang, Zengran Wang, Yukang Shi, Jianjian Sun, Zeming Li

In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection. Our work is based on a key observation -- depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

megvii-basedetection/bevdepth officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AAAI id aaai_25233 (that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ZRandomize/MatrixVT mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic... (arXiv:2209.10248; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Object DetectionDepth EstimationObject DetectionRobust Camera Only 3D Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection DAIR-V2X-I BEVDepth AP|R40(easy) 75.7 #4 of 9 Archive leaderboard report
3D Object Detection DAIR-V2X-I BEVDepth AP|R40(hard) 63.7 #4 of 9 Archive leaderboard report
3D Object Detection DAIR-V2X-I BEVDepth AP|R40(moderate) 63.6 #4 of 9 Archive leaderboard report
3D Object Detection Rope3D BEVDepth AP@0.7 42.56 #4 of 8 Archive leaderboard report
3D Object Detection nuScenes Camera Only BEVDepth-pure Future Frame false #13 of 19 Archive leaderboard report
3D Object Detection nuScenes Camera Only BEVDepth-pure NDS 60.9 #13 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEEDTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections