{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:46:02Z","timestamp":1784133962849,"version":"3.55.0"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of Chinaunder","award":["62171251"],"award-info":[{"award-number":["62171251"]}]},{"name":"National Natural Science Foundation of Chinaunder","award":["62311530100"],"award-info":[{"award-number":["62311530100"]}]},{"name":"Special Foundations for the Development of Strategic Emerging Industries of Shenzhen","award":["KJZD20231023094700001"],"award-info":[{"award-number":["KJZD20231023094700001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3498003","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T18:37:23Z","timestamp":1731609443000},"page":"1578-1593","source":"Crossref","is-referenced-by-count":16,"title":["DiffI2I: Efficient Diffusion Model for Image-to-Image Translation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5583-3275","authenticated-orcid":false,"given":"Bin","family":"Xia","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6970-0140","authenticated-orcid":false,"given":"Shiyin","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7559-4152","authenticated-orcid":false,"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5860-5941","authenticated-orcid":false,"given":"Xinglong","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1423-4513","authenticated-orcid":false,"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-1286","authenticated-orcid":false,"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Timotfe","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, IFI & CAIDAS, University of Würzburg, Würzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3445-5711","authenticated-orcid":false,"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref4","article-title":"Knowledge distillation based degradation estimation for blind super-resolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref5","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref6","article-title":"SeaFormer: Squeeze-enhanced axial transformer for mobile semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wan"},{"key":"ref7","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref9","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref10","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref11","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref18","article-title":"EdgeConnect: Generative image inpainting with adversarial edge learning","author":"Nazeri","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref23","article-title":"VA-DepthNet: A variational approach to single image depth prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088914"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965927"},{"key":"ref27","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00219"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00895"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref37","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref39","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref40","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref46","article-title":"DepthFormer: Exploiting long-range correlation and local information for accurate monocular depth estimation","author":"Li","year":"2022"},{"key":"ref47","article-title":"BinsFormer: Revisiting adaptive bins for monocular depth estimation","author":"Li","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186715"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2968521"},{"issue":"7","key":"ref57","first-page":"8874","article-title":"Reference-based image and video super-resolution via $ c^{2}$c2-matching","volume":"45","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3194090"},{"key":"ref59","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref60","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref61","first-page":"27 953","article-title":"Flexible diffusion modeling of long videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Harvey"},{"key":"ref62","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref63","article-title":"Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem","author":"Trippe","year":"2022"},{"key":"ref64","article-title":"Protein structure and sequence generation with equivariant denoising diffusion probabilistic models","author":"Anand","year":"2022"},{"key":"ref65","article-title":"Denoising diffusion restoration models","author":"Kawar","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"ref67","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2022"},{"key":"ref68","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","volume-title":"Proc. Int. Conf. Med. Imag. Deep Learn.","author":"Wolleb"},{"key":"ref69","article-title":"Monocular depth estimation using diffusion models","author":"Saxena","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref71","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02444"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref77","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref78","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref80","article-title":"Progressive growing of GAnNs for improved quality, stability, and variation","author":"Karras","year":"2017"},{"key":"ref81","article-title":"Large scale image completion via co-modulated generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref83","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref84","first-page":"1905","article-title":"eal-ESRGAN: Training real-world blind super-resolution with pure synthetic data","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Wang"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00255"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00442"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00318"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"ref90","first-page":"711","article-title":"On single image scale-up using sparse-representations","volume-title":"Proc. Int. Conf. Curves Surfaces","author":"Zeyde"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4020-z"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00328"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00779"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20030"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_4"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00567"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.147"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00267"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00897"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00853"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00397"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_20"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00613"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00366"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref115","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref121","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16282"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref132","first-page":"1","article-title":"DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref133","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10752976.pdf?arnumber=10752976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:04:04Z","timestamp":1738821844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":133,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3498003","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}