{"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-ghost-free-shadow-removal-via-dual","title":"Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN","arxiv_id":"1911.08718","date":"2019-11-20","proceeding":null,"authors":["Xiaodong Cun","Chi-Man Pun","Cheng Shi"],"abstract":"Shadow removal is an essential task for scene understanding. Many studies consider only matching the image contents, which often causes two types of ghosts: color in-consistencies in shadow regions or artifacts on shadow boundaries. In this paper, we tackle these issues in two ways. First, to carefully learn the border artifacts-free image, we propose a novel network structure named the dual hierarchically aggregation network~(DHAN). It contains a series of growth dilated convolutions as the backbone without any down-samplings, and we hierarchically aggregate multi-context features for attention and prediction, respectively. Second, we argue that training on a limited dataset restricts the textural understanding of the network, which leads to the shadow region color in-consistencies. Currently, the largest dataset contains 2k+ shadow/shadow-free image pairs. However, it has only 0.1k+ unique scenes since many samples share exactly the same background with different shadow positions. Thus, we design a shadow matting generative adversarial network~(SMGAN) to synthesize realistic shadow mattings from a given shadow mask and shadow-free image. With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images. Experiments show that our DHAN can erase the shadows and produce high-quality ghost-free images. After training on the synthesized and real datasets, our network outperforms other state-of-the-art methods by a large margin. The code is available: http://github.com/vinthony/ghost-free-shadow-removal/","url_abs":"https://arxiv.org/abs/1911.08718v2","url_pdf":"https://arxiv.org/pdf/1911.08718v2.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-ghost-free-shadow-removal-via-dual","repo_url":"https://github.com/vinthony/ghost-free-shadow-removal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-ghost-free-shadow-removal-via-dual","repo_url":"https://github.com/mducducd/Shadow-Removal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-ghost-free-shadow-removal-via-dual","repo_url":"https://github.com/mducducd/ghost-free-shadow-removal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-ghost-free-shadow-removal-via-dual","repo_url":"https://github.com/nachifur/DMTN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-ghost-free-shadow-removal-via-dual","repo_url":"https://github.com/CV-Reimplementation/DHAN-reimplementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-removal-on-istd","task":"Shadow Removal","dataset":"ISTD","model":"DHAN+DA","rank_in_archive_order":4,"of":10,"metrics":{"MAE":"5.76"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd","task":"Shadow Removal","dataset":"ISTD","model":"DHAN","rank_in_archive_order":6,"of":10,"metrics":{"MAE":"6.37"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.08718","atlas_url":"https://app.syntology.ai/?focus=1911.08718","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":"1911.08718"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1911.08718\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1911.08718"},"call":"get_concepts_for_paper(arxiv_id=\"1911.08718\")"}],"by_repo":[{"repo":"vinthony/ghost-free-shadow-removal","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mducducd/Shadow-Removal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mducducd/ghost-free-shadow-removal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nachifur/DMTN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CV-Reimplementation/DHAN-reimplementation","kind":"listed","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":"6203ac0e0d5ea3ec5ded06d1bf965e922acba8ab88c7de148f1f42931dd7d0d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}