{"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/dc-shadownet-single-image-hard-and-soft-1","title":"DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network","arxiv_id":"2207.10434","date":"2022-07-21","proceeding":"ICCV 2021 10","authors":["Yeying Jin","Aashish Sharma","Robby T. Tan"],"abstract":"Shadow removal from a single image is generally still an open problem. Most existing learning-based methods use supervised learning and require a large number of paired images (shadow and corresponding non-shadow images) for training. A recent unsupervised method, Mask-ShadowGAN~\\cite{Hu19}, addresses this limitation. However, it requires a binary mask to represent shadow regions, making it inapplicable to soft shadows. To address the problem, in this paper, we propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet. Specifically, we propose to integrate a shadow/shadow-free domain classifier into a generator and its discriminator, enabling them to focus on shadow regions. To train our network, we introduce novel losses based on physics-based shadow-free chromaticity, shadow-robust perceptual features, and boundary smoothness. Moreover, we show that our unsupervised network can be used for test-time training that further improves the results. Our experiments show that all these novel components allow our method to handle soft shadows, and also to perform better on hard shadows both quantitatively and qualitatively than the existing state-of-the-art shadow removal methods. Our code is available at: \\url{https://github.com/jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal}.","url_abs":"https://arxiv.org/abs/2207.10434v2","url_pdf":"https://arxiv.org/pdf/2207.10434v2.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":"dc-shadownet-single-image-hard-and-soft-1","repo_url":"https://github.com/jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-shadow-removal","task_name":"Image Shadow Removal"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-removal-on-istd","task":"Shadow Removal","dataset":"ISTD","model":"DC-ShadowNet","rank_in_archive_order":5,"of":10,"metrics":{"MAE":"5.88"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"DC-ShadowNet (ICCV 2021) (512x512)","rank_in_archive_order":22,"of":26,"metrics":{"LPIPS":"0.234","PSNR":"26.06","RMSE":"3.64","SSIM":"0.835"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"DC-ShadowNet (ICCV 2021) (256x256)","rank_in_archive_order":25,"of":26,"metrics":{"LPIPS":"0.406","PSNR":"25.18","RMSE":"3.89","SSIM":"0.693"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"DC-ShadowNet (ICCV 2021) (512x512)","rank_in_archive_order":3,"of":25,"metrics":{"LPIPS":"0.255","PSNR":"26.47","RMSE":"3.68","SSIM":"0.808"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"DC-ShadowNet (ICCV 2021) (256x256)","rank_in_archive_order":12,"of":25,"metrics":{"LPIPS":"0.383","PSNR":"24.72","RMSE":"4.27","SSIM":"0.67"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.10434","atlas_url":"https://app.syntology.ai/?focus=2207.10434","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":"2207.10434"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.10434\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.10434"},"call":"get_concepts_for_paper(arxiv_id=\"2207.10434\")"}],"by_repo":[{"repo":"jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal","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":"fa69354678e03c7108f09a871b39d4456246f9a5f9f80db92bc53cdff83d4ea3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}