{"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/progressive-semantic-aware-style","title":"Progressive Semantic-Aware Style Transformation for Blind Face Restoration","arxiv_id":"2009.08709","date":"2020-09-18","proceeding":"CVPR 2021 1","authors":["Chaofeng Chen","Xiaoming Li","Lingbo Yang","Xianhui Lin","Lei Zhang","Kwan-Yee K. Wong"],"abstract":"Face restoration is important in face image processing, and has been widely studied in recent years. However, previous works often fail to generate plausible high quality (HQ) results for real-world low quality (LQ) face images. In this paper, we propose a new progressive semantic-aware style transformation framework, named PSFR-GAN, for face restoration. Specifically, instead of using an encoder-decoder framework as previous methods, we formulate the restoration of LQ face images as a multi-scale progressive restoration procedure through semantic-aware style transformation. Given a pair of LQ face image and its corresponding parsing map, we first generate a multi-scale pyramid of the inputs, and then progressively modulate different scale features from coarse-to-fine in a semantic-aware style transfer way. Compared with previous networks, the proposed PSFR-GAN makes full use of the semantic (parsing maps) and pixel (LQ images) space information from different scales of input pairs. In addition, we further introduce a semantic aware style loss which calculates the feature style loss for each semantic region individually to improve the details of face textures. Finally, we pretrain a face parsing network which can generate decent parsing maps from real-world LQ face images. Experiment results show that our model trained with synthetic data can not only produce more realistic high-resolution results for synthetic LQ inputs and but also generalize better to natural LQ face images compared with state-of-the-art methods. Codes are available at https://github.com/chaofengc/PSFRGAN.","url_abs":"https://arxiv.org/abs/2009.08709v2","url_pdf":"https://arxiv.org/pdf/2009.08709v2.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":"progressive-semantic-aware-style","repo_url":"https://github.com/chaofengc/PSFRGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"blind-face-restoration","task_name":"Blind Face Restoration"},{"task_slug":"face-parsing","task_name":"Face Parsing"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"psfr-gan","method_name":"PSFR-GAN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"psfr-gan","name":"PSFR-GAN","full_name":"PSFR-GAN"}],"results":[{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"PSFRGAN","rank_in_archive_order":4,"of":15,"metrics":{"Deg.":"39.69","FID":"47.59","LPIPS":"42.4","NIQE":"5.123","PSNR":"24.71","SSIM":"0.6557"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.08709","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}