{"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/3d-shape-reconstruction-from-sketches-via","title":"3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks","arxiv_id":"1707.06375","date":"2017-07-20","proceeding":null,"authors":["Zhaoliang Lun","Matheus Gadelha","Evangelos Kalogerakis","Subhransu Maji","Rui Wang"],"abstract":"We propose a method for reconstructing 3D shapes from 2D sketches in the form\nof line drawings. Our method takes as input a single sketch, or multiple\nsketches, and outputs a dense point cloud representing a 3D reconstruction of\nthe input sketch(es). The point cloud is then converted into a polygon mesh. At\nthe heart of our method lies a deep, encoder-decoder network. The encoder\nconverts the sketch into a compact representation encoding shape information.\nThe decoder converts this representation into depth and normal maps capturing\nthe underlying surface from several output viewpoints. The multi-view maps are\nthen consolidated into a 3D point cloud by solving an optimization problem that\nfuses depth and normals across all viewpoints. Based on our experiments,\ncompared to other methods, such as volumetric networks, our architecture offers\nseveral advantages, including more faithful reconstruction, higher output\nsurface resolution, better preservation of topology and shape structure.","url_abs":"http://arxiv.org/abs/1707.06375v3","url_pdf":"http://arxiv.org/pdf/1707.06375v3.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":"3d-shape-reconstruction-from-sketches-via","repo_url":"https://github.com/EnvisageIITM/HoloJest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"3d-shape-reconstruction-from-sketches-via","repo_url":"https://github.com/LONG-9621/SketchTo3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"3d-shape-reconstruction-from-sketches-via","repo_url":"https://github.com/aghinsa/SketchTo3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-shape-reconstruction","task_name":"3D Shape Reconstruction"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.06375","atlas_url":"https://app.syntology.ai/?focus=1707.06375","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}