{"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/interpretable-edge-enhancement-and","title":"Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation","arxiv_id":"2209.09483","date":"2022-09-20","proceeding":null,"authors":["Haoyi Xiu","Xin Liu","Weimin WANG","Kyoung-Sook Kim","Takayuki Shinohara","Qiong Chang","Masashi Matsuoka"],"abstract":"3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware methods incorporate edge modeling into network designs to better describe local structures. Although these methods show that incorporating edge information is beneficial, how edge information helps remains unclear, making it difficult for users to analyze its usefulness. To shed light on this issue, in this study, we propose a new algorithm called Diffusion Unit (DU) that handles edge information in a principled and interpretable manner while providing decent improvement. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments and analyses performed on challenging benchmarks verify the effectiveness of DU. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code is available at https://github.com/martianxiu/DiffusionUnit.","url_abs":"https://arxiv.org/abs/2209.09483v3","url_pdf":"https://arxiv.org/pdf/2209.09483v3.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":"interpretable-edge-enhancement-and","repo_url":"https://github.com/martianxiu/diffusionunit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"Diffusion Unit","rank_in_archive_order":6,"of":67,"metrics":{"Class Average IoU":"85.2","Instance Average IoU":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"Diffusion Unit","rank_in_archive_order":22,"of":61,"metrics":{"Number of params":"8.1M","mAcc":"78.1","mIoU":"72.2","oAcc":"91.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}