{"url":"/method/ispl","slug":"ispl","name":"ISPL","full_name":"Implicit Subspace Prior Learning","full_name_withheld":false,"description_markdown":"**Implicit Subspace Prior Learning**, or **ISPL**, is a framework to approach dual-blind face restoration, with two major distinctions from previous restoration methods: 1) Instead of assuming an explicit degradation function between LQ and HQ domain, it establishes an implicit correspondence between both domains via a mutual embedding space, thus avoid solving the pathological inverse problem directly. 2) A subspace prior decomposition and fusion mechanism to dynamically handle inputs at varying degradation levels with consistent high-quality restoration results.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Implicit Subspace Prior Learning for Dual-Blind Face Restoration","paper":"/paper/implicit-subspace-prior-learning-for-dual","first_author":"Lingbo Yang","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/implicit-subspace-prior-learning-for-dual"},"source":{"url":"https://arxiv.org/abs/2010.05508v1","title":"Implicit Subspace Prior Learning for Dual-Blind Face Restoration","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Face Restoration Models","url":"/methods/category/face-restoration-models","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":"/paper/robust-meta-learning-with-sampling-noise-and-1","title":"Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile","date":"2022-06-04","arxiv_id":"2206.01944","n_code_links":1,"syntology":null},{"paper":null,"title":"Robust Meta-learning with Noise via Eigen-Reptile","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/implicit-subspace-prior-learning-for-dual","title":"Implicit Subspace Prior Learning for Dual-Blind Face Restoration","date":"2020-10-12","arxiv_id":"2010.05508","n_code_links":1,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":2},{"task":"/task/meta-learning","name":"Meta-Learning","papers":2},{"task":"/task/blind-face-restoration","name":"Blind Face Restoration","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ispl"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}