Papers › Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

31 Dec 2020arXiv:2012.15712archive 2025-07-28

Jiajun Deng, Shaoshuai Shi, Peiwei Li, Wengang Zhou, Yanyong Zhang, Houqiang Li

Recent advances on 3D object detection heavily rely on how the 3D data are represented, \emph{i.e.}, voxel-based or point-based representation. Many existing high performance 3D detectors are point-based because this structure can better retain precise point positions. Nevertheless, point-level features lead to high computation overheads due to unordered storage. In contrast, the voxel-based structure is better suited for feature extraction but often yields lower accuracy because the input data are divided into grids. In this paper, we take a slightly different viewpoint -- we find that precise positioning of raw points is not essential for high performance 3D object detection and that the coarse voxel granularity can also offer sufficient detection accuracy. Bearing this view in mind, we devise a simple but effective voxel-based framework, named Voxel R-CNN. By taking full advantage of voxel features in a two stage approach, our method achieves comparable detection accuracy with state-of-the-art point-based models, but at a fraction of the computation cost. Voxel R-CNN consists of a 3D backbone network, a 2D bird-eye-view (BEV) Region Proposal Network and a detect head. A voxel RoI pooling is devised to extract RoI features directly from voxel features for further refinement. Extensive experiments are conducted on the widely used KITTI Dataset and the more recent Waymo Open Dataset. Our results show that compared to existing voxel-based methods, Voxel R-CNN delivers a higher detection accuracy while maintaining a real-time frame processing rate, \emph{i.e}., at a speed of 25 FPS on an NVIDIA RTX 2080 Ti GPU. The code is available at \url{https://github.com/djiajunustc/Voxel-R-CNN}.

PaperPDFConference PDFCode

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

Code

djiajunustc/Voxel-R-CNN officialmentioned in papermentioned on GitHubpytorch report
open-mmlab/OpenPCDet officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
KangchengLiu/RM3D mentioned on GitHubpytorch report
Sidu28/Voxel_att mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

3D Object DetectionObject DetectionRegion ProposalVocal Bursts Intensity Predictionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection KITTI Cars Easy val Voxel R-CNN AP 89.41 #6 of 11 Archive leaderboard report
3D Object Detection KITTI Cars Hard Voxel R-CNN AP 77.06 #6 of 25 Archive leaderboard report
3D Object Detection KITTI Cars Hard val Voxel R-CNN AP 78.93 #6 of 10 Archive leaderboard report
3D Object Detection KITTI Cars Moderate val Voxel R-CNN AP 84.52 #4 of 11 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

Introduced by this paper: Voxel RoI Pooling

Max PoolingRPNVoxel RoI Pooling

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