{"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/scatterformer-efficient-voxel-transformer","title":"ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention","arxiv_id":"2401.00912","date":"2024-01-01","proceeding":null,"authors":["Chenhang He","Ruihuang Li","Guowen Zhang","Lei Zhang"],"abstract":"Window-based transformers excel in large-scale point cloud understanding by capturing context-aware representations with affordable attention computation in a more localized manner. However, the sparse nature of point clouds leads to a significant variance in the number of voxels per window. Existing methods group the voxels in each window into fixed-length sequences through extensive sorting and padding operations, resulting in a non-negligible computational and memory overhead. In this paper, we introduce ScatterFormer, which to the best of our knowledge, is the first to directly apply attention to voxels across different windows as a single sequence. The key of ScatterFormer is a Scattered Linear Attention (SLA) module, which leverages the pre-computation of key-value pairs in linear attention to enable parallel computation on the variable-length voxel sequences divided by windows. Leveraging the hierarchical structure of GPUs and shared memory, we propose a chunk-wise algorithm that reduces the SLA module's latency to less than 1 millisecond on moderate GPUs. Furthermore, we develop a cross-window interaction module that improves the locality and connectivity of voxel features across different windows, eliminating the need for extensive window shifting. Our proposed ScatterFormer demonstrates 73.8 mAP (L2) on the Waymo Open Dataset and 72.4 NDS on the NuScenes dataset, running at an outstanding detection rate of 23 FPS.The code is available at \\href{https://github.com/skyhehe123/ScatterFormer}{https://github.com/skyhehe123/ScatterFormer}.","url_abs":"https://arxiv.org/abs/2401.00912v2","url_pdf":"https://arxiv.org/pdf/2401.00912v2.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":"scatterformer-efficient-voxel-transformer","repo_url":"https://github.com/skyhehe123/scatterformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"blocking","task_name":"Blocking"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.00912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00912"}},"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":"deterministic:regex_extraction","url":"https://github.com/skyhehe123/ScatterFormer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"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":"0d095007c24b14c0","entry":"post_act_block_dense","repo":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/models/backbones_3d/spconv_backbone_2d.py","file_url":"https://github.com/skyhehe123/ScatterFormer/blob/HEAD/pcdet/models/backbones_3d/spconv_backbone_2d.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d095007c24b14c0"}},{"code_sha256_prefix":"44db2351bcc0bffe","entry":"cfg_from_yaml_file","repo":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/skyhehe123/ScatterFormer/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":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/skyhehe123/ScatterFormer/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":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/skyhehe123/ScatterFormer/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":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/config.py","file_url":"https://github.com/skyhehe123/ScatterFormer/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":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/utils/loss_utils.py","file_url":"https://github.com/skyhehe123/ScatterFormer/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":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/models/backbones_3d/spconv_backbone.py","file_url":"https://github.com/skyhehe123/ScatterFormer/blob/HEAD/pcdet/models/backbones_3d/spconv_backbone.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"}},{"code_sha256_prefix":"016a882194742fe9","entry":"post_act_block","repo":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/models/backbones_3d/spconv_backbone_2d.py","file_url":"https://github.com/skyhehe123/ScatterFormer/blob/HEAD/pcdet/models/backbones_3d/spconv_backbone_2d.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":"016a882194742fe9"}},{"code_sha256_prefix":"3109d923a449a567","entry":"scatter_nd","repo":"skyhehe123/ScatterFormer","repo_kind":"official","path":"pcdet/models/backbones_3d/scatterformer.py","file_url":"https://github.com/skyhehe123/ScatterFormer/blob/HEAD/pcdet/models/backbones_3d/scatterformer.py","link_basis":"first_harvest_node","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":"3109d923a449a567"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}