{"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/geometry-contrastive-gan-for-facial","title":"Geometry-Contrastive GAN for Facial Expression Transfer","arxiv_id":"1802.01822","date":"2018-02-06","proceeding":null,"authors":["Fengchun Qiao","Naiming Yao","Zirui Jiao","Zhihao LI","Hui Chen","Hongan Wang"],"abstract":"In this paper, we propose a Geometry-Contrastive Generative Adversarial\nNetwork (GC-GAN) for transferring continuous emotions across different\nsubjects. Given an input face with certain emotion and a target facial\nexpression from another subject, GC-GAN can generate an identity-preserving\nface with the target expression. Geometry information is introduced into cGANs\nas continuous conditions to guide the generation of facial expressions. In\norder to handle the misalignment across different subjects or emotions,\ncontrastive learning is used to transform geometry manifold into an embedded\nsemantic manifold of facial expressions. Therefore, the embedded geometry is\ninjected into the latent space of GANs and control the emotion generation\neffectively. Experimental results demonstrate that our proposed method can be\napplied in facial expression transfer even there exist big differences in\nfacial shapes and expressions between different subjects.","url_abs":"http://arxiv.org/abs/1802.01822v2","url_pdf":"http://arxiv.org/pdf/1802.01822v2.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":"geometry-contrastive-gan-for-facial","repo_url":"https://github.com/joffery/GC-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.01822","atlas_url":"https://app.syntology.ai/?focus=1802.01822","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}