{"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/attentive-generative-adversarial-network-for","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","arxiv_id":"1711.10098","date":"2017-11-28","proceeding":"CVPR 2018 6","authors":["Rui Qian","Robby T. Tan","Wenhan Yang","Jiajun Su","Jiaying Liu"],"abstract":"Raindrops adhered to a glass window or camera lens can severely hamper the\nvisibility of a background scene and degrade an image considerably. In this\npaper, we address the problem by visually removing raindrops, and thus\ntransforming a raindrop degraded image into a clean one. The problem is\nintractable, since first the regions occluded by raindrops are not given.\nSecond, the information about the background scene of the occluded regions is\ncompletely lost for most part. To resolve the problem, we apply an attentive\ngenerative network using adversarial training. Our main idea is to inject\nvisual attention into both the generative and discriminative networks. During\nthe training, our visual attention learns about raindrop regions and their\nsurroundings. Hence, by injecting this information, the generative network will\npay more attention to the raindrop regions and the surrounding structures, and\nthe discriminative network will be able to assess the local consistency of the\nrestored regions. This injection of visual attention to both generative and\ndiscriminative networks is the main contribution of this paper. Our experiments\nshow the effectiveness of our approach, which outperforms the state of the art\nmethods quantitatively and qualitatively.","url_abs":"http://arxiv.org/abs/1711.10098v4","url_pdf":"http://arxiv.org/pdf/1711.10098v4.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":"attentive-generative-adversarial-network-for","repo_url":"https://github.com/MaybeShewill-CV/MaybeShewill-CV.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"attentive-generative-adversarial-network-for","repo_url":"https://github.com/MaybeShewill-CV/attentive-gan-derainnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"attentive-generative-adversarial-network-for","repo_url":"https://github.com/rui1996/DeRaindrop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"rain-removal","task_name":"Rain Removal"},{"task_slug":"raindrop-removal","task_name":"Raindrop Removal"}],"methods":[],"datasets_introduced":[{"slug":"raindrop","name":"Raindrop","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10098"}},"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/rui1996/DeRaindrop","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaybeShewill-CV/MaybeShewill-CV.github.io","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaybeShewill-CV/attentive-gan-derainnet","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"ran_honours":2,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"de2574207975c4e8","entry":"align_to_four","repo":"rui1996/DeRaindrop","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/rui1996/DeRaindrop/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de2574207975c4e8"}},{"code_sha256_prefix":"c69d13a733510ad1","entry":"compute_net_gradients","repo":"MaybeShewill-CV/attentive-gan-derainnet","repo_kind":"listed","path":"tools/train_model.py","file_url":"https://github.com/MaybeShewill-CV/attentive-gan-derainnet/blob/HEAD/tools/train_model.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c69d13a733510ad1"}},{"code_sha256_prefix":"1971608da6ee2771","entry":"minmax_scale","repo":"MaybeShewill-CV/attentive-gan-derainnet","repo_kind":"listed","path":"tools/test_model.py","file_url":"https://github.com/MaybeShewill-CV/attentive-gan-derainnet/blob/HEAD/tools/test_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1971608da6ee2771"}},{"code_sha256_prefix":"b056907aaf83258d","entry":"visualize_attention_map","repo":"MaybeShewill-CV/attentive-gan-derainnet","repo_kind":"listed","path":"tools/test_model.py","file_url":"https://github.com/MaybeShewill-CV/attentive-gan-derainnet/blob/HEAD/tools/test_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b056907aaf83258d"}},{"code_sha256_prefix":"05d7486897e98abd","entry":"predict","repo":"rui1996/DeRaindrop","repo_kind":"listed","path":"predict.py","file_url":"https://github.com/rui1996/DeRaindrop/blob/HEAD/predict.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":"05d7486897e98abd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}