{"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/pvnet-a-joint-convolutional-network-of-point","title":"PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition","arxiv_id":"1808.07659","date":"2018-08-23","proceeding":null,"authors":["Haoxuan You","Yifan Feng","Rongrong Ji","Yue Gao"],"abstract":"3D object recognition has attracted wide research attention in the field of\nmultimedia and computer vision. With the recent proliferation of deep learning,\nvarious deep models with different representations have achieved the\nstate-of-the-art performance. Among them, point cloud and multi-view based 3D\nshape representations are promising recently, and their corresponding deep\nmodels have shown significant performance on 3D shape recognition. However,\nthere is little effort concentrating point cloud data and multi-view data for\n3D shape representation, which is, in our consideration, beneficial and\ncompensated to each other. In this paper, we propose the Point-View Network\n(PVNet), the first framework integrating both the point cloud and the\nmulti-view data towards joint 3D shape recognition. More specifically, an\nembedding attention fusion scheme is proposed that could employ high-level\nfeatures from the multi-view data to model the intrinsic correlation and\ndiscriminability of different structure features from the point cloud data. In\nparticular, the discriminative descriptions are quantified and leveraged as the\nsoft attention mask to further refine the structure feature of the 3D shape. We\nhave evaluated the proposed method on the ModelNet40 dataset for 3D shape\nclassification and retrieval tasks. Experimental results and comparisons with\nstate-of-the-art methods demonstrate that our framework can achieve superior\nperformance.","url_abs":"http://arxiv.org/abs/1808.07659v1","url_pdf":"http://arxiv.org/pdf/1808.07659v1.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":"pvnet-a-joint-convolutional-network-of-point","repo_url":"https://github.com/code-implementation1/Code9/tree/main/PVNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"3d-shape-retrieval","task_name":"3D Shape Classification"},{"task_slug":"3d-shape-recognition","task_name":"3D Shape Recognition"},{"task_slug":"3d-shape-representation","task_name":"3D Shape Representation"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.07659","atlas_url":"https://app.syntology.ai/?focus=1808.07659","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}