{"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-to-reconstruct-texture-less","title":"Learning to Reconstruct Texture-less Deformable Surfaces from a Single View","arxiv_id":"1803.08908","date":"2018-03-23","proceeding":null,"authors":["Jan Bednařík","Pascal Fua","Mathieu Salzmann"],"abstract":"Recent years have seen the development of mature solutions for reconstructing\ndeformable surfaces from a single image, provided that they are relatively\nwell-textured. By contrast, recovering the 3D shape of texture-less surfaces\nremains an open problem, and essentially relates to Shape-from-Shading. In this\npaper, we introduce a data-driven approach to this problem. We introduce a\ngeneral framework that can predict diverse 3D representations, such as meshes,\nnormals, and depth maps. Our experiments show that meshes are ill-suited to\nhandle texture-less 3D reconstruction in our context. Furthermore, we\ndemonstrate that our approach generalizes well to unseen objects, and that it\nyields higher-quality reconstructions than a state-of-the-art SfS technique,\nparticularly in terms of normal estimates. Our reconstructions accurately model\nthe fine details of the surfaces, such as the creases of a T-Shirt worn by a\nperson.","url_abs":"http://arxiv.org/abs/1803.08908v2","url_pdf":"http://arxiv.org/pdf/1803.08908v2.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-to-reconstruct-texture-less","repo_url":"https://github.com/bednarikjan/texless_defsurf_recon","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}