{"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/deep-image-prior","title":"Deep Image Prior","arxiv_id":"1711.10925","date":"2017-11-29","proceeding":"CVPR 2018 6","authors":["Dmitry Ulyanov","Andrea Vedaldi","Victor Lempitsky"],"abstract":"Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, and inpainting. Furthermore, the same prior can be used to invert deep neural representations to diagnose them, and to restore images based on flash-no flash input pairs. Apart from its diverse applications, our approach highlights the inductive bias captured by standard generator network architectures. It also bridges the gap between two very popular families of image restoration methods: learning-based methods using deep convolutional networks and learning-free methods based on handcrafted image priors such as self-similarity. Code and supplementary material are available at https://dmitryulyanov.github.io/deep_image_prior .","url_abs":"https://arxiv.org/abs/1711.10925v4","url_pdf":"https://arxiv.org/pdf/1711.10925v4.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":"deep-image-prior","repo_url":"https://github.com/YilinLiu97/Faster-DIP-Recon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/anushka-s/Image-restoration-using-deep-image-prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/dniku/perceptual-gradient-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/hongpeng-guo/deep-image-prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/lavolpiana/deep-image-prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/lzhengchun/deep-image-prior-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/rsin46/deep-image-prior-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/safwankdb/Deep-Image-Prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/yilinliu97/fasterdip-devil-in-upsampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/yyunon/reproducibility-project-group-71","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/zekedran/deep_image_prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/DmitryUlyanov/deep-image-prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/KunStats/Paddle-DIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"unanswered"}},{"paper_slug":"deep-image-prior","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Image_Prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"feature-upsampling","task_name":"Feature Upsampling"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"jpeg-compression-artifact-reduction","task_name":"Jpeg Compression Artifact Reduction"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10925"}},"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/zekedran/deep_image_prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rsin46/deep-image-prior-keras","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lavolpiana/deep-image-prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hongpeng-guo/deep-image-prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/safwankdb/Deep-Image-Prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anushka-s/Image-restoration-using-deep-image-prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YilinLiu97/Faster-DIP-Recon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dniku/perceptual-gradient-networks","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yyunon/reproducibility-project-group-71","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KunStats/Paddle-DIP","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Image_Prior","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DmitryUlyanov/deep-image-prior","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lzhengchun/deep-image-prior-tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yilinliu97/fasterdip-devil-in-upsampling","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"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":6,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"e3edcd371d85dd22","entry":"act","repo":"dniku/perceptual-gradient-networks","repo_kind":"listed","path":"archs/deep_image_prior/common.py","file_url":"https://github.com/dniku/perceptual-gradient-networks/blob/HEAD/archs/deep_image_prior/common.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e3edcd371d85dd22"}},{"code_sha256_prefix":"cd7e7024386fb823","entry":"bn","repo":"dniku/perceptual-gradient-networks","repo_kind":"listed","path":"archs/deep_image_prior/common.py","file_url":"https://github.com/dniku/perceptual-gradient-networks/blob/HEAD/archs/deep_image_prior/common.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cd7e7024386fb823"}},{"code_sha256_prefix":"040cc21cdcd6aae9","entry":"conv","repo":"dniku/perceptual-gradient-networks","repo_kind":"listed","path":"archs/deep_image_prior/common.py","file_url":"https://github.com/dniku/perceptual-gradient-networks/blob/HEAD/archs/deep_image_prior/common.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"040cc21cdcd6aae9"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"5be41c66fa843db4","entry":"forward_backward","repo":"dniku/perceptual-gradient-networks","repo_kind":"listed","path":"train_pgn.py","file_url":"https://github.com/dniku/perceptual-gradient-networks/blob/HEAD/train_pgn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5be41c66fa843db4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}