{"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/double-dip-unsupervised-image-decomposition","title":"\"Double-DIP\": Unsupervised Image Decomposition via Coupled Deep-Image-Priors","arxiv_id":"1812.00467","date":"2018-12-02","proceeding":"Computer Vision Foundation 2018 12","authors":["Yossi Gandelsman","Assaf Shocher","Michal Irani"],"abstract":"Many seemingly unrelated computer vision tasks can be viewed as a special\ncase of image decomposition into separate layers. For example, image\nsegmentation (separation into foreground and background layers); transparent\nlayer separation (into reflection and transmission layers); Image dehazing\n(separation into a clear image and a haze map), and more. In this paper we\npropose a unified framework for unsupervised layer decomposition of a single\nimage, based on coupled \"Deep-image-Prior\" (DIP) networks. It was shown\n[Ulyanov et al] that the structure of a single DIP generator network is\nsufficient to capture the low-level statistics of a single image. We show that\ncoupling multiple such DIPs provides a powerful tool for decomposing images\ninto their basic components, for a wide variety of applications. This\ncapability stems from the fact that the internal statistics of a mixture of\nlayers is more complex than the statistics of each of its individual\ncomponents. We show the power of this approach for Image-Dehazing, Fg/Bg\nSegmentation, Watermark-Removal, Transparency Separation in images and video,\nand more. These capabilities are achieved in a totally unsupervised way, with\nno training examples other than the input image/video itself.","url_abs":"http://arxiv.org/abs/1812.00467v2","url_pdf":"http://arxiv.org/pdf/1812.00467v2.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":"double-dip-unsupervised-image-decomposition","repo_url":"https://github.com/yossigandelsman/DoubleDIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"transparency-separation","task_name":"Transparency Separation"},{"task_slug":"unsupervised-image-decomposition","task_name":"Unsupervised Image Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.00467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00467"}},"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/yossigandelsman/DoubleDIP","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"1020f902b64812e7","entry":"get_dark_channel","repo":"yossigandelsman/DoubleDIP","repo_kind":"listed","path":"dehazing.py","file_url":"https://github.com/yossigandelsman/DoubleDIP/blob/HEAD/dehazing.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1020f902b64812e7"}},{"code_sha256_prefix":"94a1fce6ec617be9","entry":"get_atmosphere","repo":"yossigandelsman/DoubleDIP","repo_kind":"listed","path":"dehazing.py","file_url":"https://github.com/yossigandelsman/DoubleDIP/blob/HEAD/dehazing.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":"94a1fce6ec617be9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}