{"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/reversible-decoupling-network-for-single","title":"Reversible Decoupling Network for Single Image Reflection Removal","arxiv_id":"2410.08063","date":"2024-10-10","proceeding":"CVPR 2025 1","authors":["Hao Zhao","Mingjia Li","Qiming Hu","Xiaojie Guo"],"abstract":"Recent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of dual-stream interaction networks. However, according to the Information Bottleneck principle, high-level semantic clues tend to be compressed or discarded during layer-by-layer propagation. Additionally, interactions in dual-stream networks follow a fixed pattern across different layers, limiting overall performance. To address these limitations, we propose a novel architecture called Reversible Decoupling Network (RDNet), which employs a reversible encoder to secure valuable information while flexibly decoupling transmission- and reflection-relevant features during the forward pass. Furthermore, we customize a transmission-rate-aware prompt generator to dynamically calibrate features, further boosting performance. Extensive experiments demonstrate the superiority of RDNet over existing SOTA methods on five widely-adopted benchmark datasets. RDNet achieves the best performance in the NTIRE 2025 Single Image Reflection Removal in the Wild Challenge in both fidelity and perceptual comparison. Our code is available at https://github.com/lime-j/RDNet","url_abs":"https://arxiv.org/abs/2410.08063v2","url_pdf":"https://arxiv.org/pdf/2410.08063v2.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":"reversible-decoupling-network-for-single","repo_url":"https://github.com/lime-j/RDNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reflection-removal","task_name":"Reflection Removal"}],"methods":[{"method_slug":"rdnet","method_name":"RDNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/reflection-removal-on-nature","task":"Reflection Removal","dataset":"Nature","model":"RDNet","rank_in_archive_order":2,"of":5,"metrics":{"PSNR":"26.21","SSIM":"0.842"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-nature","task":"Reflection Removal","dataset":"Nature","model":"Zhu et al.","rank_in_archive_order":3,"of":5,"metrics":{"PSNR":"26.04","SSIM":"0.846"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-real20","task":"Reflection Removal","dataset":"Real20","model":"RDNet","rank_in_archive_order":1,"of":8,"metrics":{"PSNR":"25.58","SSIM":"0.846"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-sir-2-objects","task":"Reflection Removal","dataset":"SIR^2(Objects)","model":"RDNet","rank_in_archive_order":1,"of":7,"metrics":{"PSNR":"26.78","SSIM":"0.921"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-sir-2-objects","task":"Reflection Removal","dataset":"SIR^2(Objects)","model":"Zhu et al.","rank_in_archive_order":7,"of":7,"metrics":{"SSIM":"0.931"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-sir-2-postcard","task":"Reflection Removal","dataset":"SIR^2(Postcard)","model":"RDNet","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"26.33","SSIM":"0.922"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-sir-2-wild","task":"Reflection Removal","dataset":"SIR^2(Wild)","model":"RDNet","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"27.7","SSIM":"0.915"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.08063","atlas_url":"https://app.syntology.ai/?focus=2410.08063","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":"2410.08063"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.08063\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.08063"},"call":"get_concepts_for_paper(arxiv_id=\"2410.08063\")"}],"by_repo":[{"repo":"lime-j/RDNet","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":"030080101a0b410125c30f6843033ce6fc3497cfdef447615e4235e2ec35c4f4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}