[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85988-en":3,"doc-seo-85988-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85988,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Spectral Consistent Flow for One-step 3D Medical Image Translation","Spectral Consistent Flow (SC-Flow) introduces a one-step 3D medical image translation framework that evaluates a single function in latent space (1-NFE). The method reformulates cross-modality mapping as a stochastic Brownian bridge process, predicting a support regularized mean velocity field. To reduce modality entanglement, oversmoothing, and texture artifacts caused by implicit low-pass modulation, a Spectral Consistency Corrector dynamically regularizes power spectral density using learnable frequency-domain gain modulation. Experiments on four datasets show improved accuracy, consistency, and robustness across translation scenarios.","arXiv :2607 . 10627v1 [ cs .CV] 12 Jul 2026  \nSpectral Consistent Flow for One-step 3D Medical Image Translation  \nHaoqing Li 1 , Jun Shi 1 ⋆ , Mingchao Li 1 , Zehua Zhu2 ,3 , Qiwei Jia 1 , Jiong  \nShi4 ,3 , and Hong An 1  \n1 University of Science and Technology of China, Hefei, China  \n[li_haoqing@mail.ustc.edu.cn](li_haoqing@mail.ustc.edu.cn) , [shijun18@ustc.edu.cn](shijun18@ustc.edu.cn)  \n2 Department of Nuclear Medicine, The First Affiliated Hospital of USTC, Hefei, China  \n3 Division of Life Sciences and Medicine, USTC, Hefei, China  \n4 Department of Neurology, The First Affiliated Hospital of USTC, Hefei, China  \nAbstract. We present Spectral Consistent Flow (SC-Flow), a 3D medical image translation framework with a single function evaluation (1-NFE) in the latent space. This approach reformulates medical image translation as a stochastic Brownian bridge process that directly constructs a mapping between source and target modalities by predicting the support regularized mean velocity field. To mitigate modality entanglement, over-smoothing, and artifacts induced by the implicit low-pass modulation of the latent average velocity, we introduce a Spectral Consistency Corrector that dynamically regularizes the evolution of the power spectral density via learnable frequency-domain gain modulation. This mechanism establishes an explicit bridge between spatial textures and spectral energy flow, enabling the model to recover fine-grained anatomical fidelity while maintaining global structural coherence. Extensive experiments on four datasets demonstrate that SC-Flow delivers significantly more accurate, consistent, and robust performance across various translation scenarios.  \nKeywords: Medical Image Translation · Power Spectral Densit · Flow Matching  \n1 Introduction  \nMedical Image Translation (MIT) aims to learn a mapping from a source modality to a target modality, enabling reduced patient scanning time and radiation exposure while supporting comprehensive multimodal diagnosis [9, 15, 67, 69] . Unlike generic unsupervised image generation [20, 24, 40, 48], MIT benefits from paired images with precise anatomical alignment. An effective framework should leverage this pairing to model complex cross-modal relationships while main  \ntaining anatomical fidelity. However, existing methods [37, 38, 48] struggle with this challenge and rely on strong modality-or disease-specific priors, hindering ⋆ Corresponding author.  \n2 H. Li et al.  \ngeneralization across domains. Moreover, diffusion-and regression-based frameworks [37,38] are computationally expensive due to large 3D volumes and multistep voxel-wise processing, limiting the feasibility in real-time clinical scenarios.  \nFlow Matching (FM) has recently emerged as a powerful alternative for learning Continuous Normalizing Flows (CNFs) by directly aligning mappings between data and prior distributions through Ordinary Differential Equations (ODEs) [1, 10, 13, 21, 41, 42] . Its deterministic formulation allows efficient inference with only a few Neural Function Evaluations (NFEs) . For instance, MeanFlow [17] models average velocity fields instead of marginal velocity, achieving high-quality synthesis with 1-NFE. Despite this efficiency, applying FM to MIT remains non-trivial due to three major challenges: (1) underutilization of paired image information, where conventional FM does not explicitly integrate structural cues from the source modality, limiting fine-grained anatomical correspondence; (2) oversmoothing and artifact formation, which degrade texture fidelity in generated images; and (3) modality entanglement, where features from source and target domains mix, compromising anatomical or metabolic accuracy.  \nTo overcome these limitations, we propose Spectral Consistent Flow (SCFlow), an efficient 1-NFE framework for 3D medical image translation. It introduces a stochastic Brownian Bridge process [31, 36] to construct MeanFlow mappings across modalities, fully exploiting pa","cbCaief0IPhzIYyi","https://ap.wps.com/l/cbCaief0IPhzIYyi","pdf",3356307,4,1,19,"English","en",105,"# Introduction\n## Flow Matching and Challenges\n## Proposed SC-Flow Framework\n## Spectral Consistency Correction","[{\"question\":\"What problem does SC-Flow address in one-step 3D medical image translation?\",\"answer\":\"SC-Flow targets inaccurate and inconsistent modality mapping caused by modality entanglement, oversmoothing, and high-frequency texture artifacts, while aiming for efficient 1-NFE inference in 3D translation tasks.\"},{\"question\":\"How does SC-Flow model cross-modal mapping between source and target modalities?\",\"answer\":\"SC-Flow reformulates the translation as a stochastic Brownian bridge process in latent space, constructing a mapping by predicting a support regularized mean velocity field.\"},{\"question\":\"What role does the Spectral Consistency Corrector (SCC) play?\",\"answer\":\"The SCC dynamically regularizes the power spectral density via learnable frequency-domain gain modulation, compensating for high-frequency energy loss to better preserve anatomical fine details while maintaining global structure.\"}]",1784207599,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"spectral-consistent-flow-for-one-step-3d-medical-image-translation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/spectral-consistent-flow-for-one-step-3d-medical-image-translation/85988/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does SC-Flow address in one-step 3D medical image translation?","Question",{"text":75,"@type":76},"SC-Flow targets inaccurate and inconsistent modality mapping caused by modality entanglement, oversmoothing, and high-frequency texture artifacts, while aiming for efficient 1-NFE inference in 3D translation tasks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does SC-Flow model cross-modal mapping between source and target modalities?",{"text":80,"@type":76},"SC-Flow reformulates the translation as a stochastic Brownian bridge process in latent space, constructing a mapping by predicting a support regularized mean velocity field.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does the Spectral Consistency Corrector (SCC) play?",{"text":84,"@type":76},"The SCC dynamically regularizes the power spectral density via learnable frequency-domain gain modulation, compensating for high-frequency energy loss to better preserve anatomical fine details while maintaining global structure.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]