{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:06:57Z","timestamp":1755223617342,"version":"3.43.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Michigan Institute for Computational Discovery and Engineering"},{"name":"KLA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Imaging"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tci.2025.3587407","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:52Z","timestamp":1752103252000},"page":"980-991","source":"Crossref","is-referenced-by-count":0,"title":["Test-Time Adaptation Improves Inverse Problem Solving With Patch-Based Diffusion Models"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5709-1909","authenticated-orcid":false,"given":"Jason","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-3315","authenticated-orcid":false,"given":"Jeffrey A.","family":"Fessler","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5942-3196","authenticated-orcid":false,"given":"Liyue","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"25683","article-title":"Improving diffusion models for inverse problems using manifold constraints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chung","year":"2022"},{"key":"ref2","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chung","year":"2023"},{"key":"ref3","first-page":"89584","article-title":"Diffusionblend: Learning 3D image prior through position-aware diffusion score blending for 3D computed tomography reconstruction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2024"},{"key":"ref4","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref5","first-page":"21757","article-title":"Snips: Solving noisy inverse problems stochastically","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kawar","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2024.3458418"},{"key":"ref7","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref9","article-title":"Solving inverse problems in medical imaging with score-based generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2022"},{"key":"ref10","first-page":"14938","article-title":"Robust compressed sensing MRI with deep generative priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Jalal","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00965"},{"key":"ref12","article-title":"Neural approximate mirror maps for constrained diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00226"},{"issue":"supplement 1","key":"ref15","article-title":"Reducing spect acquisition time by predicting missing projections with single-scan self-supervised coordinate-based learning","volume-title":"J. Nucl. Med.","volume":"64","author":"Li","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2003.12.020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3524797"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_25"},{"key":"ref19","first-page":"72137","article-title":"Patch diffusion: Faster and more data-efficient training of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref20","article-title":"Patched denoising diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ding","year":"2024"},{"key":"ref21","first-page":"1625","article-title":"Learning image priors through patch-based diffusion models for solving inverse problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Hu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref23","first-page":"22042","article-title":"I $^{2}$ SB: Image-to-image Schrdinger bridge","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref24","first-page":"7158","article-title":"Direct diffusion bridge using data consistency for inverse problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3344453"},{"key":"ref27","article-title":"Decomposed diffusion sampler for accelerating large-scale inverse problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chung","year":"2024"},{"key":"ref28","first-page":"23593","article-title":"Denoising diffusion restoration models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kawar","year":"2022"},{"key":"ref29","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref30","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref31","article-title":"Solving inverse problems with latent diffusion models via hard data consistency","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2023"},{"key":"ref32","first-page":"97408","article-title":"Divide-and-conquer posterior sampling for denoising diffusion priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Janati","year":"2024"},{"key":"ref33","article-title":"Improving diffusion models for inverse problems using optimal posterior covariance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2865198"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970104"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3094062"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2599778"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2979062"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2024.3477329"},{"key":"ref41","first-page":"5546","article-title":"Plug-and-play methods provably converge with properly trained denoisers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ryu","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1117\/12.643267"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01303-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682856"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00504"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2022.3233188"},{"key":"ref47","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref48","article-title":"Fine-tuning diffusion models with limited data","volume-title":"Proc. NeurIPS 2022 Workshop Score-Based Methods","author":"Moon","year":"2022"},{"article-title":"Spectrum-aware parameter efficient fine-tuning for diffusion models","year":"2024","author":"Zhang","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02498-0"},{"key":"ref51","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12345"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref55","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Karras","year":"2022"},{"article-title":"Odl: Operator discretization library","year":"2022","author":"Team","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443410"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897639"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2024.3369404"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28378"}],"container-title":["IEEE Transactions on Computational Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6745852\/10833176\/11074715.pdf?arnumber=11074715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T05:22:18Z","timestamp":1754976138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11074715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tci.2025.3587407","relation":{},"ISSN":["2333-9403","2334-0118","2573-0436"],"issn-type":[{"type":"electronic","value":"2333-9403"},{"type":"electronic","value":"2334-0118"},{"type":"print","value":"2573-0436"}],"subject":[],"published":{"date-parts":[[2025]]}}}