{"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/large-scale-image-completion-via-co-modulated-1","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","arxiv_id":"2103.10428","date":"2021-03-18","proceeding":"ICLR 2021 1","authors":["Shengyu Zhao","Jonathan Cui","Yilun Sheng","Yue Dong","Xiao Liang","Eric I Chang","Yan Xu"],"abstract":"Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-scale missing regions. To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations. Also, due to the lack of good quantitative metrics for image completion, we propose the new Paired/Unpaired Inception Discriminative Score (P-IDS/U-IDS), which robustly measures the perceptual fidelity of inpainted images compared to real images via linear separability in a feature space. Experiments demonstrate superior performance in terms of both quality and diversity over state-of-the-art methods in free-form image completion and easy generalization to image-to-image translation. Code is available at https://github.com/zsyzzsoft/co-mod-gan.","url_abs":"https://arxiv.org/abs/2103.10428v1","url_pdf":"https://arxiv.org/pdf/2103.10428v1.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":"large-scale-image-completion-via-co-modulated-1","repo_url":"https://github.com/zsyzzsoft/co-mod-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-inpainting-on-celeba-hq","task":"Image Inpainting","dataset":"CelebA-HQ","model":"CoModGAN","rank_in_archive_order":3,"of":6,"metrics":{"FID":"5.65","P-IDS":"11.23","U-IDS":"22.54"},"uses_additional_data":false},{"leaderboard":"/sota/image-inpainting-on-ffhq-512-x-512","task":"Image Inpainting","dataset":"FFHQ 512 x 512","model":"CoModGAN","rank_in_archive_order":3,"of":3,"metrics":{"FID":"3.7","P-IDS":"16.6%","U-IDS":"29.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-inpainting-on-places2-1","task":"Image Inpainting","dataset":"Places2","model":"CoModGAN","rank_in_archive_order":4,"of":14,"metrics":{"FID":"2.92","P-IDS":"19.64","U-IDS":"35.78"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.10428","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}