{"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/a-variational-u-net-for-conditional","title":"A Variational U-Net for Conditional Appearance and Shape Generation","arxiv_id":"1804.04694","date":"2018-04-12","proceeding":"CVPR 2018 6","authors":["Patrick Esser","Ekaterina Sutter","Björn Ommer"],"abstract":"Deep generative models have demonstrated great performance in image\nsynthesis. However, results deteriorate in case of spatial deformations, since\nthey generate images of objects directly, rather than modeling the intricate\ninterplay of their inherent shape and appearance. We present a conditional\nU-Net for shape-guided image generation, conditioned on the output of a\nvariational autoencoder for appearance. The approach is trained end-to-end on\nimages, without requiring samples of the same object with varying pose or\nappearance. Experiments show that the model enables conditional image\ngeneration and transfer. Therefore, either shape or appearance can be retained\nfrom a query image, while freely altering the other. Moreover, appearance can\nbe sampled due to its stochastic latent representation, while preserving shape.\nIn quantitative and qualitative experiments on COCO, DeepFashion, shoes,\nMarket-1501 and handbags, the approach demonstrates significant improvements\nover the state-of-the-art.","url_abs":"http://arxiv.org/abs/1804.04694v1","url_pdf":"http://arxiv.org/pdf/1804.04694v1.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":"a-variational-u-net-for-conditional","repo_url":"https://github.com/CompVis/vunet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-variational-u-net-for-conditional","repo_url":"https://github.com/jhaux/VUNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.04694","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}