{"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/submanifold-sparse-convolutional-networks","title":"Submanifold Sparse Convolutional Networks","arxiv_id":"1706.01307","date":"2017-06-05","proceeding":null,"authors":["Benjamin Graham","Laurens van der Maaten"],"abstract":"Convolutional network are the de-facto standard for analysing spatio-temporal\ndata such as images, videos, 3D shapes, etc. Whilst some of this data is\nnaturally dense (for instance, photos), many other data sources are inherently\nsparse. Examples include pen-strokes forming on a piece of paper, or (colored)\n3D point clouds that were obtained using a LiDAR scanner or RGB-D camera.\nStandard \"dense\" implementations of convolutional networks are very inefficient\nwhen applied on such sparse data. We introduce a sparse convolutional operation\ntailored to processing sparse data that differs from prior work on sparse\nconvolutional networks in that it operates strictly on submanifolds, rather\nthan \"dilating\" the observation with every layer in the network. Our empirical\nanalysis of the resulting submanifold sparse convolutional networks shows that\nthey perform on par with state-of-the-art methods whilst requiring\nsubstantially less computation.","url_abs":"http://arxiv.org/abs/1706.01307v1","url_pdf":"http://arxiv.org/pdf/1706.01307v1.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":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/facebookresearch/SparseConvNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/LONG-9621/SparseConvNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/ZHC1992/SparseConvNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/btgraham/SparseConvNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/casr-hku/esda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/sumo-agarwal/submanifold-sparse-conv-sparseconvnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/uber/sbnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"submanifold-sparse-convolutional-networks","repo_url":"https://github.com/isl-org/Open3D-ML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"}],"methods":[{"method_slug":"sparse-convolutions","method_name":"Sparse Convolutions"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"SSCN","rank_in_archive_order":37,"of":67,"metrics":{"Instance Average IoU":"86.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.01307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.01307"}},"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/btgraham/SparseConvNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber/sbnet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sumo-agarwal/submanifold-sparse-conv-sparseconvnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isl-org/Open3D-ML","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LONG-9621/SparseConvNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZHC1992/SparseConvNet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/casr-hku/esda","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/SparseConvNet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_fixture":1,"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"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":4,"samples":[{"code_sha256_prefix":"5cba07500e9d8295","entry":"calculate_grid","repo":"isl-org/Open3D-ML","repo_kind":"listed","path":"ml3d/torch/models/sparseconvnet.py","file_url":"https://github.com/isl-org/Open3D-ML/blob/HEAD/ml3d/torch/models/sparseconvnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5cba07500e9d8295"}},{"code_sha256_prefix":"942a1165c398c1ac","entry":"inter","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"942a1165c398c1ac"}},{"code_sha256_prefix":"656eb43c072b101d","entry":"iou","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"656eb43c072b101d"}},{"code_sha256_prefix":"8f73e90ab7d020f0","entry":"union","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8f73e90ab7d020f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}