{"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/projected-distribution-loss-for-image","title":"Projected Distribution Loss for Image Enhancement","arxiv_id":"2012.09289","date":"2020-12-16","proceeding":null,"authors":["Mauricio Delbracio","Hossein Talebi","Peyman Milanfar"],"abstract":"Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the choice of the distance function between input and target features may have a consequential impact on the performance of the trained model. While using the norm of the difference between extracted features leads to limited hallucination of details, measuring the distance between distributions of features may generate more textures; yet also more unrealistic details and artifacts. In this paper, we demonstrate that aggregating 1D-Wasserstein distances between CNN activations is more reliable than the existing approaches, and it can significantly improve the perceptual performance of enhancement models. More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art on reference-based perceptual losses. This means that the proposed learning loss can be plugged into different imaging frameworks and produce perceptually realistic results.","url_abs":"https://arxiv.org/abs/2012.09289v2","url_pdf":"https://arxiv.org/pdf/2012.09289v2.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":"projected-distribution-loss-for-image","repo_url":"https://github.com/HilaManor/Generative-deep-features","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"projected-distribution-loss-for-image","repo_url":"https://github.com/saurabh-kataria/projected-distribution-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"projected-distribution-loss-for-image","repo_url":"https://github.com/MindCode-4/code-8/tree/main/Projected-Distribution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"projected-distribution-loss-for-image","repo_url":"https://github.com/MindSpore-scientific/code-5/tree/main/Projected-Distribution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"jpeg-artifact-removal","task_name":"JPEG Artifact Removal"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.09289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09289"}},"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/MindCode-4/code-8/tree/main/Projected-Distribution","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-5/tree/main/Projected-Distribution","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HilaManor/Generative-deep-features","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saurabh-kataria/projected-distribution-loss","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"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":"6f918286f2607c7e","entry":"projectedDistributionLoss","repo":"saurabh-kataria/projected-distribution-loss","repo_kind":"listed","path":"pdl.py","file_url":"https://github.com/saurabh-kataria/projected-distribution-loss/blob/HEAD/pdl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f918286f2607c7e"}},{"code_sha256_prefix":"15ec8132fa5070b2","entry":"slicedWassersteinLoss","repo":"saurabh-kataria/projected-distribution-loss","repo_kind":"listed","path":"swd.py","file_url":"https://github.com/saurabh-kataria/projected-distribution-loss/blob/HEAD/swd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15ec8132fa5070b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}