{"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/learning-discriminative-3d-shape","title":"Learning Discriminative 3D Shape Representations by View Discerning Networks","arxiv_id":"1808.03823","date":"2018-08-11","proceeding":null,"authors":["Biao Leng","Cheng Zhang","Xiaocheng Zhou","Cheng Xu","Kai Xu"],"abstract":"In view-based 3D shape recognition, extracting discriminative visual\nrepresentation of 3D shapes from projected images is considered the core\nproblem. Projections with low discriminative ability can adversely influence\nthe final 3D shape representation. Especially under the real situations with\nbackground clutter and object occlusion, the adverse effect is even more\nsevere. To resolve this problem, we propose a novel deep neural network, View\nDiscerning Network, which learns to judge the quality of views and adjust their\ncontributions to the representation of shapes. In this network, a Score\nGeneration Unit is devised to evaluate the quality of each projected image with\nscore vectors. These score vectors are used to weight the image features and\nthe weighted features perform much better than original features in 3D shape\nrecognition task. In particular, we introduce two structures of Score\nGeneration Unit, Channel-wise Score Unit and Part-wise Score Unit, to assess\nthe quality of feature maps from different perspectives. Our network aggregates\nfeatures and scores in an end-to-end framework, so that final shape descriptors\nare directly obtained from its output. Our experiments on ModelNet and ShapeNet\nCore55 show that View Discerning Network outperforms the state-of-the-arts in\nterms of the retrieval task, with excellent robustness against background\nclutter and object occlusion.","url_abs":"http://arxiv.org/abs/1808.03823v2","url_pdf":"http://arxiv.org/pdf/1808.03823v2.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-discriminative-3d-shape","repo_url":"https://github.com/ChengXu1995/test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-discriminative-3d-shape","repo_url":"https://github.com/chengz3906/View-Discerning-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-shape-recognition","task_name":"3D Shape Recognition"},{"task_slug":"3d-shape-representation","task_name":"3D Shape Representation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}