{"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/learning-to-deblur-using-light-field","title":"Learning to Deblur using Light Field Generated and Real Defocus Images","arxiv_id":"2204.00367","date":"2022-04-01","proceeding":"CVPR 2022 1","authors":["Lingyan Ruan","Bin Chen","Jizhou Li","Miuling Lam"],"abstract":"Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. While deep learning approach shows great promise in solving image restoration problems, defocus deblurring demands accurate training data that consists of all-in-focus and defocus image pairs, which is difficult to collect. Naive two-shot capturing cannot achieve pixel-wise correspondence between the defocused and all-in-focus image pairs. Synthetic aperture of light fields is suggested to be a more reliable way to generate accurate image pairs. However, the defocus blur generated from light field data is different from that of the images captured with a traditional digital camera. In this paper, we propose a novel deep defocus deblurring network that leverages the strength and overcomes the shortcoming of light fields. We first train the network on a light field-generated dataset for its highly accurate image correspondence. Then, we fine-tune the network using feature loss on another dataset collected by the two-shot method to alleviate the differences between the defocus blur exists in the two domains. This strategy is proved to be highly effective and able to achieve the state-of-the-art performance both quantitatively and qualitatively on multiple test sets. Extensive ablation studies have been conducted to analyze the effect of each network module to the final performance.","url_abs":"https://arxiv.org/abs/2204.00367v1","url_pdf":"https://arxiv.org/pdf/2204.00367v1.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":"learning-to-deblur-using-light-field","repo_url":"https://github.com/lingyanruan/DRBNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-defocus-deblurring","task_name":"Image Defocus Deblurring"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.00367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00367"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lingyanruan/DRBNet","reach":null}],"summary":{"ran":2,"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"e8062fb9418a742b","entry":"DRBNet_single","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8062fb9418a742b"}},{"code_sha256_prefix":"bf4b608a6912eeb1","entry":"FAC","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bf4b608a6912eeb1"}},{"code_sha256_prefix":"f39d89d686cad3a5","entry":"ResnetBlock","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f39d89d686cad3a5"}},{"code_sha256_prefix":"3b7e8eedfa7b815f","entry":"conv","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3b7e8eedfa7b815f"}},{"code_sha256_prefix":"8e4f6ca76775258e","entry":"resnet_block","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8e4f6ca76775258e"}},{"code_sha256_prefix":"9e64ae5487522dab","entry":"upconv","repo":"lingyanruan/DRBNet","repo_kind":"official","path":"models/DRBNet.py","file_url":"https://github.com/lingyanruan/DRBNet/blob/HEAD/models/DRBNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9e64ae5487522dab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}