{"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/l2m-gan-learning-to-manipulate-latent-space","title":"L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute Editing","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Guoxing Yang","Nanyi Fei","Mingyu Ding","Guangzhen Liu","Zhiwu Lu","Tao Xiang"],"abstract":"    A deep facial attribute editing model strives to meet two requirements: (1) attribute correctness -- the target attribute should correctly appear on the edited face image; (2) irrelevance preservation -- any irrelevant information (e.g., identity) should not be changed after editing. Meeting both requirements challenges the state-of-the-art works which resort to either spatial attention or latent space factorization. Specifically, the former assume that each attribute has well-defined local support regions; they are often more effective for editing a local attribute than a global one. The latter factorize the latent space of a fixed pretrained GAN into different attribute-relevant parts, but they cannot be trained end-to-end with the GAN, leading to sub-optimal solutions. To overcome these limitations, we propose a novel latent space factorization model, called L2M-GAN, which is learned end-to-end and effective for editing both local and global attributes. The key novel components are: (1) A latent space vector of the GAN is factorized into an attribute-relevant and irrelevant codes with an orthogonality constraint imposed to ensure disentanglement. (2) An attribute-relevant code transformer is learned to manipulate the attribute value; crucially, the transformed code are subject to the same orthogonality constraint. By forcing both the original attribute-relevant latent code and the edited code to be disentangled from any attribute-irrelevant code, our model strikes the perfect balance between attribute correctness and irrelevance preservation. Extensive experiments on CelebA-HQ show that our L2M-GAN achieves significant improvements over the state-of-the-arts.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Yang_L2M-GAN_Learning_To_Manipulate_Latent_Space_Semantics_for_Facial_Attribute_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Yang_L2M-GAN_Learning_To_Manipulate_Latent_Space_Semantics_for_Facial_Attribute_CVPR_2021_paper.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":"l2m-gan-learning-to-manipulate-latent-space","repo_url":"https://github.com/rucmlcv/L2M-GAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"l2m-gan-learning-to-manipulate-latent-space","repo_url":"https://github.com/songquanpeng/L2M-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}