{"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/condaformer-disassembled-transformer-with-1","title":"ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding","arxiv_id":"2312.11112","date":"2023-12-18","proceeding":"NeurIPS 2023 11","authors":["Lunhao Duan","Shanshan Zhao","Nan Xue","Mingming Gong","Gui-Song Xia","DaCheng Tao"],"abstract":"Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved. A large number of points, over 0.1 million, make the global self-attention infeasible for point cloud data. Thus, most methods propose to apply the transformer in a local region, e.g., spherical or cubic window. However, it still contains a large number of Query-Key pairs, which requires high computational costs. In addition, previous methods usually learn the query, key, and value using a linear projection without modeling the local 3D geometric structure. In this paper, we attempt to reduce the costs and model the local geometry prior by developing a new transformer block, named ConDaFormer. Technically, ConDaFormer disassembles the cubic window into three orthogonal 2D planes, leading to fewer points when modeling the attention in a similar range. The disassembling operation is beneficial to enlarging the range of attention without increasing the computational complexity, but ignores some contexts. To provide a remedy, we develop a local structure enhancement strategy that introduces a depth-wise convolution before and after the attention. This scheme can also capture the local geometric information. Taking advantage of these designs, ConDaFormer captures both long-range contextual information and local priors. The effectiveness is demonstrated by experimental results on several 3D point cloud understanding benchmarks. Code is available at https://github.com/LHDuan/ConDaFormer .","url_abs":"https://arxiv.org/abs/2312.11112v1","url_pdf":"https://arxiv.org/pdf/2312.11112v1.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":"condaformer-disassembled-transformer-with-1","repo_url":"https://github.com/lhduan/condaformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"ConDaFormer","rank_in_archive_order":9,"of":61,"metrics":{"mAcc":"78.9","mIoU":"73.5","oAcc":"92.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.11112","atlas_url":"https://app.syntology.ai/?focus=2312.11112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11112"}},"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":"deterministic:regex_extraction","url":"https://github.com/LHDuan/ConDaFormer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lhduan/condaformer","reach":{"status":"ok"}}],"summary":{"ran_violates":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":9,"samples":[{"code_sha256_prefix":"5f4f4355be28c01e","entry":"isnan","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/utils/losses.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/utils/losses.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f4f4355be28c01e"}},{"code_sha256_prefix":"e85b5d21dc5b8382","entry":"lovasz_grad","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/utils/losses.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e85b5d21dc5b8382"}},{"code_sha256_prefix":"2a2c9e53188de780","entry":"batch2offset","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/utils.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/utils.py","link_basis":"harvester_set","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":"2a2c9e53188de780"}},{"code_sha256_prefix":"66d6bb150bbb2e57","entry":"grid_sample","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/condaformer/utils.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/condaformer/utils.py","link_basis":"plan_row","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":"66d6bb150bbb2e57"}},{"code_sha256_prefix":"82b9b0ff4b3626c9","entry":"lovasz_softmax","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/utils/losses.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/utils/losses.py","link_basis":"plan_row","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":"82b9b0ff4b3626c9"}},{"code_sha256_prefix":"6dd8eac8666461f5","entry":"offset2batch","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/condaformer/condaformer.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/condaformer/condaformer.py","link_basis":"plan_row","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":"6dd8eac8666461f5"}},{"code_sha256_prefix":"d78aee4794314c59","entry":"offset2batch","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/utils.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/utils.py","link_basis":"plan_row","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":"d78aee4794314c59"}},{"code_sha256_prefix":"ae72b160c77cb3e4","entry":"to_3d_numpy","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/condaformer/utils.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/condaformer/utils.py","link_basis":"plan_row","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":"ae72b160c77cb3e4"}},{"code_sha256_prefix":"5436174f8c0e64e0","entry":"trunc_normal_","repo":"lhduan/condaformer","repo_kind":"official","path":"pcr/models/utils.py","file_url":"https://github.com/lhduan/condaformer/blob/HEAD/pcr/models/utils.py","link_basis":"harvester_set","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":"5436174f8c0e64e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}