{"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/view-synthesis-by-appearance-flow","title":"View Synthesis by Appearance Flow","arxiv_id":"1605.03557","date":"2016-05-11","proceeding":null,"authors":["Tinghui Zhou","Shubham Tulsiani","Weilun Sun","Jitendra Malik","Alexei A. Efros"],"abstract":"We address the problem of novel view synthesis: given an input image,\nsynthesizing new images of the same object or scene observed from arbitrary\nviewpoints. We approach this as a learning task but, critically, instead of\nlearning to synthesize pixels from scratch, we learn to copy them from the\ninput image. Our approach exploits the observation that the visual appearance\nof different views of the same instance is highly correlated, and such\ncorrelation could be explicitly learned by training a convolutional neural\nnetwork (CNN) to predict appearance flows -- 2-D coordinate vectors specifying\nwhich pixels in the input view could be used to reconstruct the target view.\nFurthermore, the proposed framework easily generalizes to multiple input views\nby learning how to optimally combine single-view predictions. We show that for\nboth objects and scenes, our approach is able to synthesize novel views of\nhigher perceptual quality than previous CNN-based techniques.","url_abs":"http://arxiv.org/abs/1605.03557v3","url_pdf":"http://arxiv.org/pdf/1605.03557v3.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":"view-synthesis-by-appearance-flow","repo_url":"https://github.com/Chinmay26/Multi-Viewpoint-Image-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"view-synthesis-by-appearance-flow","repo_url":"https://github.com/RenYurui/Global-Flow-Local-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"view-synthesis-by-appearance-flow","repo_url":"https://github.com/andrewjong/Global-Flow-Local-Attention-VTryon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"view-synthesis-by-appearance-flow","repo_url":"https://github.com/tinghuiz/appearance-flow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.03557","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}