{"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/iterative-residual-network-for-deep-joint","title":"Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network","arxiv_id":"1807.06403","date":"2018-07-16","proceeding":null,"authors":["Filippos Kokkinos","Stamatios Lefkimmiatis"],"abstract":"Modern digital cameras rely on the sequential execution of separate image\nprocessing steps to produce realistic images. The first two steps are usually\nrelated to denoising and demosaicking where the former aims to reduce noise\nfrom the sensor and the latter converts a series of light intensity readings to\ncolor images. Modern approaches try to jointly solve these problems, i.e. joint\ndenoising-demosaicking which is an inherently ill-posed problem given that\ntwo-thirds of the intensity information is missing and the rest are perturbed\nby noise. While there are several machine learning systems that have been\nrecently introduced to solve this problem, the majority of them relies on\ngeneric network architectures which do not explicitly take into account the\nphysical image model. In this work we propose a novel algorithm which is\ninspired by powerful classical image regularization methods, large-scale\noptimization, and deep learning techniques. Consequently, our derived iterative\noptimization algorithm, which involves a trainable denoising network, has a\ntransparent and clear interpretation compared to other black-box data driven\napproaches. Our extensive experimentation line demonstrates that our proposed\nmethod outperforms any previous approaches for both noisy and noise-free data\nacross many different datasets. This improvement in reconstruction quality is\nattributed to the rigorous derivation of an iterative solution and the\nprincipled way we design our denoising network architecture, which as a result\nrequires fewer trainable parameters than the current state-of-the-art solution\nand furthermore can be efficiently trained by using a significantly smaller\nnumber of training data than existing deep demosaicking networks. Code and\nresults can be found at https://github.com/cig-skoltech/deep_demosaick","url_abs":"http://arxiv.org/abs/1807.06403v3","url_pdf":"http://arxiv.org/pdf/1807.06403v3.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":"iterative-residual-network-for-deep-joint","repo_url":"https://github.com/cig-skoltech/deep_demosaick","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.06403","atlas_url":"https://app.syntology.ai/?focus=1807.06403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.06403"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/cig-skoltech/deep_demosaick","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":"b796a109116d0d4e","entry":"mse_loss","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"l2proj.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/l2proj.py","link_basis":"harvester_set","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":"b796a109116d0d4e"}},{"code_sha256_prefix":"1e4f3112f7b76130","entry":"apply_colortransformation_gamma","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"utils.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/utils.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":"1e4f3112f7b76130"}},{"code_sha256_prefix":"793420e18aeaca47","entry":"bilinear","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"MMNet_TBPTT.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/MMNet_TBPTT.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":"793420e18aeaca47"}},{"code_sha256_prefix":"1f80f003de17602a","entry":"conv3x3","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"residual_model_resdnet.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/residual_model_resdnet.py","link_basis":"harvester_set","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":"1f80f003de17602a"}},{"code_sha256_prefix":"8613e957a52d9399","entry":"downsampling","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"problems.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/problems.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":"8613e957a52d9399"}},{"code_sha256_prefix":"d3da1ab483f6f5bb","entry":"load_resdnet_params","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"utils.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/utils.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":"d3da1ab483f6f5bb"}},{"code_sha256_prefix":"d2b7eb267eaa3c3e","entry":"load_theta_npy","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"data_loaders/rgb_transform.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/data_loaders/rgb_transform.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":"d2b7eb267eaa3c3e"}},{"code_sha256_prefix":"6d2b553b27ab79d7","entry":"loadmat","repo":"cig-skoltech/deep_demosaick","repo_kind":"official","path":"utils.py","file_url":"https://github.com/cig-skoltech/deep_demosaick/blob/HEAD/utils.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":"6d2b553b27ab79d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}