{"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/photoshape-photorealistic-materials-for-large","title":"PhotoShape: Photorealistic Materials for Large-Scale Shape Collections","arxiv_id":"1809.09761","date":"2018-09-26","proceeding":null,"authors":["Keunhong Park","Konstantinos Rematas","Ali Farhadi","Steven M. Seitz"],"abstract":"Existing online 3D shape repositories contain thousands of 3D models but lack\nphotorealistic appearance. We present an approach to automatically assign\nhigh-quality, realistic appearance models to large scale 3D shape collections.\nThe key idea is to jointly leverage three types of online data -- shape\ncollections, material collections, and photo collections, using the photos as\nreference to guide assignment of materials to shapes. By generating a large\nnumber of synthetic renderings, we train a convolutional neural network to\nclassify materials in real photos, and employ 3D-2D alignment techniques to\ntransfer materials to different parts of each shape model. Our system produces\nphotorealistic, relightable, 3D shapes (PhotoShapes).","url_abs":"http://arxiv.org/abs/1809.09761v1","url_pdf":"http://arxiv.org/pdf/1809.09761v1.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":"photoshape-photorealistic-materials-for-large","repo_url":"https://github.com/keunhong/photoshape","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"photoshape","name":"PhotoShape","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.09761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}