{"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/towards-robust-blind-face-restoration-with","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","arxiv_id":"2206.11253","date":"2022-06-22","proceeding":null,"authors":["Shangchen Zhou","Kelvin C. K. Chan","Chongyi Li","Chen Change Loy"],"abstract":"Blind face restoration is a highly ill-posed problem that often requires auxiliary guidance to 1) improve the mapping from degraded inputs to desired outputs, or 2) complement high-quality details lost in the inputs. In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces. Under this paradigm, we propose a Transformer-based prediction network, named CodeFormer, to model the global composition and context of the low-quality faces for code prediction, enabling the discovery of natural faces that closely approximate the target faces even when the inputs are severely degraded. To enhance the adaptiveness for different degradation, we also propose a controllable feature transformation module that allows a flexible trade-off between fidelity and quality. Thanks to the expressive codebook prior and global modeling, CodeFormer outperforms the state of the arts in both quality and fidelity, showing superior robustness to degradation. Extensive experimental results on synthetic and real-world datasets verify the effectiveness of our method.","url_abs":"https://arxiv.org/abs/2206.11253v2","url_pdf":"https://arxiv.org/pdf/2206.11253v2.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":"towards-robust-blind-face-restoration-with","repo_url":"https://github.com/sczhou/codeformer","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":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset":"CelebA-Test","model":"CodeFormer","rank_in_archive_order":1,"of":15,"metrics":{"FID":"60.62","IDS":"60","LPIPS":"29.9","PSNR":"22.18","SSIM":"0.61"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"GFP-GAN","rank_in_archive_order":3,"of":9,"metrics":{"FID":"49.96"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"PSFRGAN","rank_in_archive_order":4,"of":9,"metrics":{"FID":"51.89"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"CodeFormer","rank_in_archive_order":5,"of":9,"metrics":{"FID":"52.02"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"GLEAN","rank_in_archive_order":6,"of":9,"metrics":{"FID":"53.49"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"GPEN","rank_in_archive_order":7,"of":9,"metrics":{"FID":"57.58"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"DFDNet","rank_in_archive_order":8,"of":9,"metrics":{"FID":"62.57"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-lfw","task":"Blind Face Restoration","dataset":"LFW","model":"PULSE","rank_in_archive_order":9,"of":9,"metrics":{"FID":"64.86"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"CodeFormer","rank_in_archive_order":3,"of":9,"metrics":{"FID":"39.06"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"GFP-GAN","rank_in_archive_order":4,"of":9,"metrics":{"FID":"40.59"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"GPEN","rank_in_archive_order":5,"of":9,"metrics":{"FID":"46.99"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"GLEAN","rank_in_archive_order":6,"of":9,"metrics":{"FID":"47.11"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"PSFRGAN","rank_in_archive_order":7,"of":9,"metrics":{"FID":"51.16"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"DFDNet","rank_in_archive_order":8,"of":9,"metrics":{"FID":"57.84"},"uses_additional_data":false},{"leaderboard":"/sota/blind-face-restoration-on-wider","task":"Blind Face Restoration","dataset":"WIDER","model":"PULSE","rank_in_archive_order":9,"of":9,"metrics":{"FID":"73.59"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.11253","atlas_url":"https://app.syntology.ai/?focus=2206.11253","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":"2206.11253"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2206.11253\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2206.11253"},"call":"get_concepts_for_paper(arxiv_id=\"2206.11253\")"}],"by_repo":[{"repo":"sczhou/codeformer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"91fdfade15fd319a5804efaf7ce6b78e808ea10f6ad2b005d779c5a5a3640100","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}