{"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/voxelnext-fully-sparse-voxelnet-for-3d-object-1","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","arxiv_id":"2303.11301","date":"2023-03-20","proceeding":"CVPR 2023 1","authors":["Yukang Chen","Jianhui Liu","Xiangyu Zhang","Xiaojuan Qi","Jiaya Jia"],"abstract":"3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.","url_abs":"https://arxiv.org/abs/2303.11301v1","url_pdf":"https://arxiv.org/pdf/2303.11301v1.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":"voxelnext-fully-sparse-voxelnet-for-3d-object-1","repo_url":"https://github.com/dvlab-research/VoxelNeXt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"voxelnext-fully-sparse-voxelnet-for-3d-object-1","repo_url":"https://github.com/dvlab-research/3d-box-segment-anything","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-multi-object-tracking-on-nuscenes-lidar","task":"3D Multi-Object Tracking","dataset":"nuScenes LiDAR only","model":"VoxelNeXt","rank_in_archive_order":1,"of":1,"metrics":{"AMOTA":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-argoverse2","task":"3D Object Detection","dataset":"Argoverse2","model":"VoxelNeXt","rank_in_archive_order":2,"of":2,"metrics":{"mAP":"30.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11301","atlas_url":"https://app.syntology.ai/?focus=2303.11301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11301"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dvlab-research/3d-box-segment-anything","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/dvlab-research/VoxelNeXt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"44db2351bcc0bffe","entry":"cfg_from_yaml_file","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"44db2351bcc0bffe"}},{"code_sha256_prefix":"65fe32ede00e7dcb","entry":"compute_fg_mask","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/utils/loss_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"65fe32ede00e7dcb"}},{"code_sha256_prefix":"1780d388cc532a6d","entry":"get_corner_loss_lidar","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/utils/loss_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1780d388cc532a6d"}},{"code_sha256_prefix":"50e8e8cdfc5129f0","entry":"merge_new_config","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50e8e8cdfc5129f0"}},{"code_sha256_prefix":"488b91d67a807558","entry":"neg_loss_cornernet","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/utils/loss_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"488b91d67a807558"}},{"code_sha256_prefix":"2b4e0558df870bf9","entry":"post_act_block","repo":"dvlab-research/VoxelNeXt","repo_kind":"official","path":"pcdet/models/backbones_3d/spconv_backbone_voxelnext.py","file_url":"https://github.com/dvlab-research/VoxelNeXt/blob/HEAD/pcdet/models/backbones_3d/spconv_backbone_voxelnext.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2b4e0558df870bf9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}