{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/difface-blind-face-restoration-with-diffused","title":"DifFace: Blind Face Restoration with Diffused Error Contraction","arxiv_id":"2212.06512","date":"2022-12-13","proceeding":null,"authors":["Zongsheng Yue","Chen Change Loy"],"abstract":"While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data. Second, these methods require multiple constraints, e.g., fidelity, perceptual, and adversarial losses, which require laborious hyper-parameter tuning to stabilize and balance their influences. In this work, we propose a novel method named DifFace that is capable of coping with unseen and complex degradations more gracefully without complicated loss designs. The key of our method is to establish a posterior distribution from the observed low-quality (LQ) image to its high-quality (HQ) counterpart. In particular, we design a transition distribution from the LQ image to the intermediate state of a pre-trained diffusion model and then gradually transmit from this intermediate state to the HQ target by recursively applying a pre-trained diffusion model. The transition distribution only relies on a restoration backbone that is trained with $L_2$ loss on some synthetic data, which favorably avoids the cumbersome training process in existing methods. Moreover, the transition distribution can contract the error of the restoration backbone and thus makes our method more robust to unknown degradations. Comprehensive experiments show that DifFace is superior to current state-of-the-art methods, especially in cases with severe degradations. Code and model are available at https://github.com/zsyOAOA/DifFace.","url_abs":"https://arxiv.org/abs/2212.06512v4","url_pdf":"https://arxiv.org/pdf/2212.06512v4.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":"difface-blind-face-restoration-with-diffused","repo_url":"https://github.com/zsyoaoa/difface","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"difface-blind-face-restoration-with-diffused","repo_url":"https://github.com/zsyoaoa/resshift","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"blind-face-restoration","task_name":"Blind Face Restoration"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"DifFace","rank_in_archive_order":5,"of":15,"metrics":{"FID":"38.43","IDS":"62.39","LPIPS":"43.5","PSNR":"24.08","SSIM":"0.703"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"GLEAN","rank_in_archive_order":8,"of":15,"metrics":{"FID":"60.3","IDS":"67.13","LPIPS":"46.9","PSNR":"23.41","SSIM":"0.666"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"VQFR","rank_in_archive_order":9,"of":15,"metrics":{"FID":"45.84","IDS":"65.87","LPIPS":"47.1","PSNR":"21.94","SSIM":"0.585"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"GFPGAN","rank_in_archive_order":11,"of":15,"metrics":{"FID":"46.99","IDS":"66.76","LPIPS":"49.5","PSNR":"22.18","SSIM":"0.631"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"PSFRGAN","rank_in_archive_order":12,"of":15,"metrics":{"FID":"52.14","IDS":"68.14","LPIPS":"50","PSNR":"22.74","SSIM":"0.63"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"PULSE","rank_in_archive_order":13,"of":15,"metrics":{"FID":"48.33","IDS":"74.97","LPIPS":"50.8","PSNR":"22.14","SSIM":"0.682"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"DFDNet","rank_in_archive_order":14,"of":15,"metrics":{"FID":"64.65","IDS":"86.21","LPIPS":"55.4","PSNR":"23.15","SSIM":"0.629"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.06512","atlas_url":"https://app.syntology.ai/?focus=2212.06512","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2212.06512"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.06512\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.06512"},"call":"get_concepts_for_paper(arxiv_id=\"2212.06512\")"}],"by_repo":[{"repo":"zsyoaoa/difface","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zsyoaoa/resshift","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.12348"],"harvested_for_calls":[{"arxiv_id":"2307.12348","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.12348"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.12348\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1b5cd53ec7a33c609d88233b8cc82e3c2974272d0d4f3fcfa7ca183f9c9d5217","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}