{"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/diverse-image-to-image-translation-via","title":"Diverse Image-to-Image Translation via Disentangled Representations","arxiv_id":"1808.00948","date":"2018-08-02","proceeding":"ECCV 2018 9","authors":["Hsin-Ying Lee","Hung-Yu Tseng","Jia-Bin Huang","Maneesh Kumar Singh","Ming-Hsuan Yang"],"abstract":"Image-to-image translation aims to learn the mapping between two visual\ndomains. There are two main challenges for many applications: 1) the lack of\naligned training pairs and 2) multiple possible outputs from a single input\nimage. In this work, we present an approach based on disentangled\nrepresentation for producing diverse outputs without paired training images. To\nachieve diversity, we propose to embed images onto two spaces: a\ndomain-invariant content space capturing shared information across domains and\na domain-specific attribute space. Our model takes the encoded content features\nextracted from a given input and the attribute vectors sampled from the\nattribute space to produce diverse outputs at test time. To handle unpaired\ntraining data, we introduce a novel cross-cycle consistency loss based on\ndisentangled representations. Qualitative results show that our model can\ngenerate diverse and realistic images on a wide range of tasks without paired\ntraining data. For quantitative comparisons, we measure realism with user study\nand diversity with a perceptual distance metric. We apply the proposed model to\ndomain adaptation and show competitive performance when compared to the\nstate-of-the-art on the MNIST-M and the LineMod datasets.","url_abs":"http://arxiv.org/abs/1808.00948v1","url_pdf":"http://arxiv.org/pdf/1808.00948v1.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":"diverse-image-to-image-translation-via","repo_url":"https://github.com/HsinYingLee/DRIT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/Bingwen-Hu/DRIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/HsinYingLee/MDMM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/Wenchao-Du/LIR-for-Unsupervised-IR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/guy-oren/DIRT-OST","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/hytseng0509/DRIT_hr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diverse-image-to-image-translation-via","repo_url":"https://github.com/taki0112/DRIT-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"multimodal-unsupervised-image-to-image","task_name":"Multimodal Unsupervised Image-To-Image Translation"},{"task_slug":"perceptual-distance","task_name":"Perceptual Distance"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-5","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"AFHQ","model":"DRIT","rank_in_archive_order":4,"of":4,"metrics":{"FID":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-4","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"CelebA-HQ","model":"DRIT","rank_in_archive_order":4,"of":4,"metrics":{"FID":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"Domain adaptation","rank_in_archive_order":62,"of":73,"metrics":{"mIoU":"43.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.00948","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}