{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-geometry-disentangled-representation","title":"Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud","arxiv_id":"2012.10921","date":"2020-12-20","proceeding":null,"authors":["Mutian Xu","Junhao Zhang","Zhipeng Zhou","Mingye Xu","Xiaojuan Qi","Yu Qiao"],"abstract":"In 2D image processing, some attempts decompose images into high and low frequency components for describing edge and smooth parts respectively. Similarly, the contour and flat area of 3D objects, such as the boundary and seat area of a chair, describe different but also complementary geometries. However, such investigation is lost in previous deep networks that understand point clouds by directly treating all points or local patches equally. To solve this problem, we propose Geometry-Disentangled Attention Network (GDANet). GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Then GDANet exploits Sharp-Gentle Complementary Attention Module that regards the features from sharp and gentle variation components as two holistic representations, and pays different attentions to them while fusing them respectively with original point cloud features. In this way, our method captures and refines the holistic and complementary 3D geometric semantics from two distinct disentangled components to supplement the local information. Extensive experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters. Code is released on https://github.com/mutianxu/GDANet.","url_abs":"https://arxiv.org/abs/2012.10921v3","url_pdf":"https://arxiv.org/pdf/2012.10921v3.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":"learning-geometry-disentangled-representation","repo_url":"https://github.com/mutianxu/GDANet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-geometry-disentangled-representation","repo_url":"https://github.com/yossilevii100/critical_points2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-geometry-disentangled-representation","repo_url":"https://github.com/yossilevii100/refocusing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"GDANet","rank_in_archive_order":21,"of":67,"metrics":{"Class Average IoU":"85.0","Instance Average IoU":"86.5"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"GDANet","rank_in_archive_order":43,"of":111,"metrics":{"Overall Accuracy":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-classification-on-pointcloud-c","task":"Point Cloud Classification","dataset":"PointCloud-C","model":"GDANet","rank_in_archive_order":14,"of":24,"metrics":{"mean Corruption Error (mCE)":"0.892"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-segmentation-on-pointcloud-c","task":"Point Cloud Segmentation","dataset":"PointCloud-C","model":"GDANet","rank_in_archive_order":1,"of":11,"metrics":{"mean Corruption Error (mCE)":"0.923"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.10921","atlas_url":"https://app.syntology.ai/?focus=2012.10921","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.10921"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.10921\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.10921"},"call":"get_concepts_for_paper(arxiv_id=\"2012.10921\")"}],"by_repo":[{"repo":"mutianxu/GDANet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yossilevii100/critical_points2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2308.05525"],"harvested_for_calls":[{"arxiv_id":"2308.05525","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.05525"},"call":"get_harvested_code_for_paper(arxiv_id=\"2308.05525\")"}]},{"repo":"yossilevii100/refocusing","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2308.05525"],"harvested_for_calls":[{"arxiv_id":"2308.05525","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.05525"},"call":"get_harvested_code_for_paper(arxiv_id=\"2308.05525\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b482b337ccb102d0a1f1d488661ae31c0952d4748bb3ecd3fc35dd944a69657b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}