{"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/auto-exposure-fusion-for-single-image-shadow","title":"Auto-Exposure Fusion for Single-Image Shadow Removal","arxiv_id":"2103.01255","date":"2021-03-01","proceeding":"CVPR 2021 1","authors":["Lan Fu","Changqing Zhou","Qing Guo","Felix Juefei-Xu","Hongkai Yu","Wei Feng","Yang Liu","Song Wang"],"abstract":"Shadow removal is still a challenging task due to its inherent background-dependent and spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful state-of-the-art deep neural networks could hardly recover traceless shadow-removed background. This paper proposes a new solution for this task by formulating it as an exposure fusion problem to address the challenges. Intuitively, we can first estimate multiple over-exposure images w.r.t. the input image to let the shadow regions in these images have the same color with shadow-free areas in the input image. Then, we fuse the original input with the over-exposure images to generate the final shadow-free counterpart. Nevertheless, the spatial-variant property of the shadow requires the fusion to be sufficiently `smart', that is, it should automatically select proper over-exposure pixels from different images to make the final output natural. To address this challenge, we propose the shadow-aware FusionNet that takes the shadow image as input to generate fusion weight maps across all the over-exposure images. Moreover, we propose the boundary-aware RefineNet to eliminate the remaining shadow trace further. We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods. We release the model and code in https://github.com/tsingqguo/exposure-fusion-shadow-removal.","url_abs":"https://arxiv.org/abs/2103.01255v2","url_pdf":"https://arxiv.org/pdf/2103.01255v2.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":"auto-exposure-fusion-for-single-image-shadow","repo_url":"https://github.com/tsingqguo/exposure-fusion-shadow-removal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"auto-exposure-fusion-for-single-image-shadow","repo_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-shadow-removal","task_name":"Image Shadow Removal"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"Auto (CVPR 2021) (512x512)","rank_in_archive_order":6,"of":26,"metrics":{"LPIPS":"0.189","PSNR":"28.07","RMSE":"2.99","SSIM":"0.853"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"Auto (CVPR 2021) (256x256)","rank_in_archive_order":21,"of":26,"metrics":{"LPIPS":"0.365","PSNR":"26.1","RMSE":"3.53","SSIM":"0.718"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"Auto (CVPR 2021) (512x512)","rank_in_archive_order":19,"of":25,"metrics":{"LPIPS":"0.247","PSNR":"24.32","RMSE":"4.71","SSIM":"0.8"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"Auto (CVPR 2021) (256x256)","rank_in_archive_order":22,"of":25,"metrics":{"LPIPS":"0.37","PSNR":"23.2","RMSE":"5.37","SSIM":"0.694"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01255"}},"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/CV-Reimplementation/AEFNet-Reimplementation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsingqguo/exposure-fusion-shadow-removal","reach":{"status":"unanswered"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tsingqguo/exposurefusion-shadow-removal","reach":{"status":"unanswered"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"973bfc25e8f16d63","entry":"GradientLoss","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"973bfc25e8f16d63"}},{"code_sha256_prefix":"1573d916ee849cff","entry":"L_TV","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1573d916ee849cff"}},{"code_sha256_prefix":"c45b6700be1cc109","entry":"tensor2im","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c45b6700be1cc109"}},{"code_sha256_prefix":"6b8739e8fabd686e","entry":"BaseModel","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b8739e8fabd686e"}},{"code_sha256_prefix":"fa0b81ea417ad17d","entry":"DistangleModel","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fa0b81ea417ad17d"}},{"code_sha256_prefix":"ffad6ea71a6ce1ff","entry":"FusionModel","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ffad6ea71a6ce1ff"}},{"code_sha256_prefix":"5162d854ad287b25","entry":"PoissonGradientLoss","repo":"CV-Reimplementation/AEFNet-Reimplementation","repo_kind":"listed","path":"models/Fusion_model.py","file_url":"https://github.com/CV-Reimplementation/AEFNet-Reimplementation/blob/HEAD/models/Fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5162d854ad287b25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}