{"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/syncspeccnn-synchronized-spectral-cnn-for-3d","title":"SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation","arxiv_id":"1612.00606","date":"2016-12-02","proceeding":"CVPR 2017 7","authors":["Li Yi","Hao Su","Xingwen Guo","Leonidas Guibas"],"abstract":"In this paper, we study the problem of semantic annotation on 3D models that\nare represented as shape graphs. A functional view is taken to represent\nlocalized information on graphs, so that annotations such as part segment or\nkeypoint are nothing but 0-1 indicator vertex functions. Compared with images\nthat are 2D grids, shape graphs are irregular and non-isomorphic data\nstructures. To enable the prediction of vertex functions on them by\nconvolutional neural networks, we resort to spectral CNN method that enables\nweight sharing by parameterizing kernels in the spectral domain spanned by\ngraph laplacian eigenbases. Under this setting, our network, named SyncSpecCNN,\nstrive to overcome two key challenges: how to share coefficients and conduct\nmulti-scale analysis in different parts of the graph for a single shape, and\nhow to share information across related but different shapes that may be\nrepresented by very different graphs. Towards these goals, we introduce a\nspectral parameterization of dilated convolutional kernels and a spectral\ntransformer network. Experimentally we tested our SyncSpecCNN on various tasks,\nincluding 3D shape part segmentation and 3D keypoint prediction.\nState-of-the-art performance has been achieved on all benchmark datasets.","url_abs":"http://arxiv.org/abs/1612.00606v1","url_pdf":"http://arxiv.org/pdf/1612.00606v1.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":[],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"SSCNN","rank_in_archive_order":58,"of":67,"metrics":{"Class Average IoU":"82.0","Instance Average IoU":"84.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.00606","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}