{"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/dual-residual-networks-leveraging-the","title":"Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration","arxiv_id":"1903.08817","date":"2019-03-21","proceeding":"CVPR 2019 6","authors":["Xing Liu","Masanori Suganuma","Zhun Sun","Takayuki Okatani"],"abstract":"In this paper, we study design of deep neural networks for tasks of image\nrestoration. We propose a novel style of residual connections dubbed \"dual\nresidual connection\", which exploits the potential of paired operations, e.g.,\nup- and down-sampling or convolution with large- and small-size kernels. We\ndesign a modular block implementing this connection style; it is equipped with\ntwo containers to which arbitrary paired operations are inserted. Adopting the\n\"unraveled\" view of the residual networks proposed by Veit et al., we point out\nthat a stack of the proposed modular blocks allows the first operation in a\nblock interact with the second operation in any subsequent blocks. Specifying\nthe two operations in each of the stacked blocks, we build a complete network\nfor each individual task of image restoration. We experimentally evaluate the\nproposed approach on five image restoration tasks using nine datasets. The\nresults show that the proposed networks with properly chosen paired operations\noutperform previous methods on almost all of the tasks and datasets.","url_abs":"http://arxiv.org/abs/1903.08817v2","url_pdf":"http://arxiv.org/pdf/1903.08817v2.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":"dual-residual-networks-leveraging-the","repo_url":"https://github.com/liu-vis/DualResidualNetworks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.08817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08817"}},"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/liu-vis/DualResidualNetworks","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"0415a04e36607241","entry":"CropSample","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/N_modules.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/N_modules.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0415a04e36607241"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/se_nets.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/se_nets.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"9916a4e524dcea05","entry":"AddNoiseToTensor","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"train/gaussian_noise.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/train/gaussian_noise.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9916a4e524dcea05"}},{"code_sha256_prefix":"17d9d8e77a9b0668","entry":"DCPDNData_loader","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/data_convertors.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/data_convertors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17d9d8e77a9b0668"}},{"code_sha256_prefix":"a8d0c9f00c240639","entry":"DataAugmentation","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/N_modules.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/N_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8d0c9f00c240639"}},{"code_sha256_prefix":"6f70596d93a25554","entry":"RESIDE_loader","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/data_convertors.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/data_convertors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f70596d93a25554"}},{"code_sha256_prefix":"8b854625c3a80e22","entry":"RainDrop_loader","repo":"liu-vis/DualResidualNetworks","repo_kind":"official","path":"pietorch/data_convertors.py","file_url":"https://github.com/liu-vis/DualResidualNetworks/blob/HEAD/pietorch/data_convertors.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b854625c3a80e22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}