{"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/toward-multimodal-image-to-image-translation","title":"Toward Multimodal Image-to-Image Translation","arxiv_id":"1711.11586","date":"2017-11-30","proceeding":"NeurIPS 2017 12","authors":["Jun-Yan Zhu","Richard Zhang","Deepak Pathak","Trevor Darrell","Alexei A. Efros","Oliver Wang","Eli Shechtman"],"abstract":"Many image-to-image translation problems are ambiguous, as a single input\nimage may correspond to multiple possible outputs. In this work, we aim to\nmodel a \\emph{distribution} of possible outputs in a conditional generative\nmodeling setting. The ambiguity of the mapping is distilled in a\nlow-dimensional latent vector, which can be randomly sampled at test time. A\ngenerator learns to map the given input, combined with this latent code, to the\noutput. We explicitly encourage the connection between output and the latent\ncode to be invertible. This helps prevent a many-to-one mapping from the latent\ncode to the output during training, also known as the problem of mode collapse,\nand produces more diverse results. We explore several variants of this approach\nby employing different training objectives, network architectures, and methods\nof injecting the latent code. Our proposed method encourages bijective\nconsistency between the latent encoding and output modes. We present a\nsystematic comparison of our method and other variants on both perceptual\nrealism and diversity.","url_abs":"http://arxiv.org/abs/1711.11586v4","url_pdf":"http://arxiv.org/pdf/1711.11586v4.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":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/junyanz/BicycleGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/Yash-10/modified_gravity_emulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/eriklindernoren/PyTorch-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/manicman1999/Sword-GAN32","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/prakashpandey9/BicycleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/tree/master/Chapter04","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"toward-multimodal-image-to-image-translation","repo_url":"https://github.com/sahilg06/BicycleGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-1","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"Edge-to-Handbags","model":"BicycleGAN","rank_in_archive_order":2,"of":4,"metrics":{"Diversity":"0.140","Quality":"51.2%"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-2","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"Edge-to-Shoes","model":"BicycleGAN","rank_in_archive_order":2,"of":4,"metrics":{"Diversity":"0.104","Quality":"56.7%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.11586","atlas_url":"https://app.syntology.ai/?focus=1711.11586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11586"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/prakashpandey9/BicycleGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manicman1999/Sword-GAN32","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/tree/master/Chapter04","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junyanz/BicycleGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yash-10/modified_gravity_emulation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sahilg06/BicycleGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eriklindernoren/PyTorch-GAN","reach":null}],"summary":{"unverified":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"c60f85fb9e4d9d05","entry":"reparameterization","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c60f85fb9e4d9d05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}