{"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-novel-gan-based-network-for-unmasking-of","title":"A Novel GAN-Based Network for Unmasking of Masked Face","arxiv_id":null,"date":"2020-03-02","proceeding":"IEEE 2020 3","authors":["Nizam Ud Din","KAMRAN JAVED","Seho Bae","Juneho Yi"],"abstract":"Recent deep learning based image editing methods have achieved promising results for\r\nremoving object in an image but fail to generate plausible results for removing large objects of complex\r\nnature, especially in facial images. The objective of this work is to remove mask objects in facial images.\r\nThis problem is challenging because (1) most of the time facial masks cover quite a large region of face\r\nthat even extends beyond the actual face boundary below chin, and (2) facial image pairs with and without\r\nmask object do not exist for training. We break the problem into two stages: mask object detection and\r\nimage completion of the removed mask region. The first stage of our model automatically produces binary\r\nsegmentation for the mask region. Then, the second stage removes the mask and synthesizes the affected\r\nregion with fine details while retaining the global coherency of face structure. For this, we have employed\r\na GAN-based network using two discriminators where one discriminator helps learn the global structure of\r\nthe face and then another discriminator comes in to focus learning on the deep missing region. To train our\r\nmodel in a supervised manner, we create a paired synthetic dataset using publicly available CelebA dataset\r\nand evaluated on real world images collected from the Internet. Our model outperforms others representative\r\nstate-of-the-art approaches both qualitatively and quantitatively.","url_abs":"https://ieeexplore.ieee.org/document/9019697","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9019697","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-novel-gan-based-network-for-unmasking-of","repo_url":"https://github.com/daviddirethucus/Face-Mask_Inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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}