Papers › Voxel Transformer for 3D Object Detection

Voxel Transformer for 3D Object Detection

6 Sep 2021ICCV 2021 10arXiv:2109.02497archive 2025-07-28

Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large context information, which is crucial for object recognition and localization, owing to the limited receptive fields. In this paper, we resolve the problem by introducing a Transformer-based architecture that enables long-range relationships between voxels by self-attention. Given the fact that non-empty voxels are naturally sparse but numerous, directly applying standard Transformer on voxels is non-trivial. To this end, we propose the sparse voxel module and the submanifold voxel module, which can operate on the empty and non-empty voxel positions effectively. To further enlarge the attention range while maintaining comparable computational overhead to the convolutional counterparts, we propose two attention mechanisms for multi-head attention in those two modules: Local Attention and Dilated Attention, and we further propose Fast Voxel Query to accelerate the querying process in multi-head attention. VoTr contains a series of sparse and submanifold voxel modules and can be applied in most voxel-based detectors. Our proposed VoTr shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Waymo Open dataset.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2109.02497")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: community (archive-listed): 7 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7unverified

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from PointsCoder/VOTR. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Attention3d PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 0c7c6562acc44963 · report
AttentionResBlock PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 488c3b965d745bf6 · report
SparseAttention3d PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 56c28897e806635f · report
SparseTensor PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 2bf156118a677e4d · report
SubMAttention3d PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 2e731d3f3ae92440 · report
VoxelTransformer PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · f9c7e918f02b31ca · report
scatter_nd PointsCoder/VOTR/pcdet/models/backbones_3d/votr_backbone.py community (archive-listed) unverified no licence file found · pointer only · 0737dd8ecef8e21b · report

Tasks

3D Object DetectionComputational EfficiencyObjectObject DetectionObject Recognitionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection waymo vehicle VoTr-TSD L1 mAP 74.95 #8 of 8 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: VoTr

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFast Voxel QueryLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVoTr

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