{"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/a-loss-function-for-generative-neural","title":"A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model","arxiv_id":"2006.15057","date":"2020-06-26","proceeding":null,"authors":["Steffen Czolbe","Oswin Krause","Ingemar Cox","Christian Igel"],"abstract":"To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity. We propose such a loss function based on Watson's perceptual model, which computes a weighted distance in frequency space and accounts for luminance and contrast masking. We extend the model to color images, increase its robustness to translation by using the Fourier Transform, remove artifacts due to splitting the image into blocks, and make it differentiable. In experiments, VAEs trained with the new loss function generated realistic, high-quality image samples. Compared to using the Euclidean distance and the Structural Similarity Index, the images were less blurry; compared to deep neural network based losses, the new approach required less computational resources and generated images with less artifacts.","url_abs":"https://arxiv.org/abs/2006.15057v3","url_pdf":"https://arxiv.org/pdf/2006.15057v3.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":"a-loss-function-for-generative-neural","repo_url":"https://github.com/SteffenCzolbe/PerceptualSimilarity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.15057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15057"}},"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/SteffenCzolbe/PerceptualSimilarity","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"89f0a16b3ee660b6","entry":"Dct2d","repo":"steffenczolbe/perceptualsimilarity","repo_kind":"official","path":"src/loss/watson.py","file_url":"https://github.com/steffenczolbe/perceptualsimilarity/blob/HEAD/src/loss/watson.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"89f0a16b3ee660b6"}},{"code_sha256_prefix":"7b46c4155a539296","entry":"WatsonDistance","repo":"steffenczolbe/perceptualsimilarity","repo_kind":"official","path":"src/loss/watson.py","file_url":"https://github.com/steffenczolbe/perceptualsimilarity/blob/HEAD/src/loss/watson.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b46c4155a539296"}},{"code_sha256_prefix":"cc287dc402b9202b","entry":"softmax","repo":"steffenczolbe/perceptualsimilarity","repo_kind":"official","path":"src/loss/watson.py","file_url":"https://github.com/steffenczolbe/perceptualsimilarity/blob/HEAD/src/loss/watson.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":"cc287dc402b9202b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}