{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/voxel-transformer-for-3d-object-detection","title":"Voxel Transformer for 3D Object Detection","arxiv_id":"2109.02497","date":"2021-09-06","proceeding":"ICCV 2021 10","authors":["Jiageng Mao","Yujing Xue","Minzhe Niu","Haoyue Bai","Jiashi Feng","Xiaodan Liang","Hang Xu","Chunjing Xu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2109.02497v2","url_pdf":"https://arxiv.org/pdf/2109.02497v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"voxel-transformer-for-3d-object-detection","repo_url":"https://github.com/PointsCoder/VOTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fast-voxel-query","method_name":"Fast Voxel Query"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"votr","method_name":"VoTr"}],"datasets_introduced":[],"methods_introduced":[{"slug":"votr","name":"VoTr","full_name":"Voxel Transformer"}],"results":[{"leaderboard":"/sota/3d-object-detection-on-waymo-vehicle","task":"3D Object Detection","dataset":"waymo vehicle","model":"VoTr-TSD","rank_in_archive_order":8,"of":8,"metrics":{"L1 mAP":"74.95"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.02497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02497"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PointsCoder/VOTR","reach":null}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"0c7c6562acc44963","entry":"Attention3d","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c7c6562acc44963"}},{"code_sha256_prefix":"488c3b965d745bf6","entry":"AttentionResBlock","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"488c3b965d745bf6"}},{"code_sha256_prefix":"56c28897e806635f","entry":"SparseAttention3d","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56c28897e806635f"}},{"code_sha256_prefix":"2bf156118a677e4d","entry":"SparseTensor","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bf156118a677e4d"}},{"code_sha256_prefix":"2e731d3f3ae92440","entry":"SubMAttention3d","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e731d3f3ae92440"}},{"code_sha256_prefix":"f9c7e918f02b31ca","entry":"VoxelTransformer","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9c7e918f02b31ca"}},{"code_sha256_prefix":"0737dd8ecef8e21b","entry":"scatter_nd","repo":"PointsCoder/VOTR","repo_kind":"listed","path":"pcdet/models/backbones_3d/votr_backbone.py","file_url":"https://github.com/PointsCoder/VOTR/blob/HEAD/pcdet/models/backbones_3d/votr_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0737dd8ecef8e21b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}