{"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/transformation-grounded-image-generation","title":"Transformation-Grounded Image Generation Network for Novel 3D View Synthesis","arxiv_id":"1703.02921","date":"2017-03-08","proceeding":"CVPR 2017 7","authors":["Eunbyung Park","Jimei Yang","Ersin Yumer","Duygu Ceylan","Alexander C. Berg"],"abstract":"We present a transformation-grounded image generation network for novel 3D\nview synthesis from a single image. Instead of taking a 'blank slate' approach,\nwe first explicitly infer the parts of the geometry visible both in the input\nand novel views and then re-cast the remaining synthesis problem as image\ncompletion. Specifically, we both predict a flow to move the pixels from the\ninput to the novel view along with a novel visibility map that helps deal with\nocculsion/disocculsion. Next, conditioned on those intermediate results, we\nhallucinate (infer) parts of the object invisible in the input image. In\naddition to the new network structure, training with a combination of\nadversarial and perceptual loss results in a reduction in common artifacts of\nnovel view synthesis such as distortions and holes, while successfully\ngenerating high frequency details and preserving visual aspects of the input\nimage. We evaluate our approach on a wide range of synthetic and real examples.\nBoth qualitative and quantitative results show our method achieves\nsignificantly better results compared to existing methods.","url_abs":"http://arxiv.org/abs/1703.02921v1","url_pdf":"http://arxiv.org/pdf/1703.02921v1.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":"transformation-grounded-image-generation","repo_url":"https://github.com/Chinmay26/Multi-Viewpoint-Image-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"transformation-grounded-image-generation","repo_url":"https://github.com/silverbottlep/tvsn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.02921","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}