{"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/resvit-residual-vision-transformers-for-multi","title":"ResViT: Residual vision transformers for multi-modal medical image synthesis","arxiv_id":"2106.16031","date":"2021-06-30","proceeding":null,"authors":["Onat Dalmaz","Mahmut Yurt","Tolga Çukur"],"abstract":"Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, that leverages the contextual sensitivity of vision transformers along with the precision of convolution operators and realism of adversarial learning.} ResViT's generator employs a central bottleneck comprising novel aggregated residual transformer (ART) blocks that synergistically combine residual convolutional and transformer modules. Residual connections in ART blocks promote diversity in captured representations, while a channel compression module distills task-relevant information. A weight sharing strategy is introduced among ART blocks to mitigate computational burden. A unified implementation is introduced to avoid the need to rebuild separate synthesis models for varying source-target modality configurations. Comprehensive demonstrations are performed for synthesizing missing sequences in multi-contrast MRI, and CT images from MRI. Our results indicate superiority of ResViT against competing CNN- and transformer-based methods in terms of qualitative observations and quantitative metrics.","url_abs":"https://arxiv.org/abs/2106.16031v3","url_pdf":"https://arxiv.org/pdf/2106.16031v3.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":"resvit-residual-vision-transformers-for-multi","repo_url":"https://github.com/icon-lab/ResViT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"resvit-residual-vision-transformers-for-multi","repo_url":"https://github.com/CV-Reimplementation/ResViT-Reimplementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-brats","task":"Image-to-Image Translation","dataset":"BRATS","model":"ResViT","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"26.90"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"ResViT","rank_in_archive_order":1,"of":7,"metrics":{"PSNR":"35.71 ± 1.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"pGAN","rank_in_archive_order":2,"of":7,"metrics":{"PSNR":"33.95 ± 1.67"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"SAGAN","rank_in_archive_order":3,"of":7,"metrics":{"PSNR":"33.71 ± 1.61"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"pix2pix","rank_in_archive_order":4,"of":7,"metrics":{"PSNR":"33.62 ± 2.07\t"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"TransUNet","rank_in_archive_order":5,"of":7,"metrics":{"PSNR":"32.49 ± 1.74"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ixi-dataset","task":"Image-to-Image Translation","dataset":"IXI","model":"A-UNet","rank_in_archive_order":6,"of":7,"metrics":{"PSNR":"32.43 ± 1.74"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.16031","atlas_url":"https://app.syntology.ai/?focus=2106.16031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.16031"}},"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/CV-Reimplementation/ResViT-Reimplementation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/icon-lab/ResViT","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"7d8eaf5537f699e4","entry":"np2th","repo":"icon-lab/ResViT","repo_kind":"official","path":"models/residual_transformers.py","file_url":"https://github.com/icon-lab/ResViT/blob/HEAD/models/residual_transformers.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d8eaf5537f699e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}