{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:13:54Z","timestamp":1778184834654,"version":"3.51.4"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Laboratory of Science, Technology and Standard in Press Industry; and in part by the Major Key Project of PCL","award":["PCL2025A03"],"award-info":[{"award-number":["PCL2025A03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3651547","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:37:39Z","timestamp":1767724659000},"page":"6211-6224","source":"Crossref","is-referenced-by-count":1,"title":["Syntax-Driven Multi-Realism Image Compression With Consistency Guided Diffusion Model"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4975-6474","authenticated-orcid":false,"given":"Haowei","family":"Kuang","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1692-0069","authenticated-orcid":false,"given":"Wenhan","family":"Yang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4944-9621","authenticated-orcid":false,"given":"Zongming","family":"Guo","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2000.838192"},{"key":"ref3","volume-title":"BPG Image Format","author":"Bellard","year":"2017"},{"key":"ref4","first-page":"1","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01686"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref12","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref13","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Mentzer"},{"key":"ref14","first-page":"25426","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muckley"},{"key":"ref15","first-page":"64971","article-title":"Lossy image compression with conditional diffusion models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"1945","article-title":"Grammar variational autoencoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusner"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00288"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref22","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref23","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"L\u00fc"},{"key":"ref24","first-page":"1622","article-title":"Consistency guided diffusion model with neural syntax for perceptual image compression","volume-title":"Proc. 32nd ACM Int. Conf. Multimedia","author":"Kuang"},{"key":"ref25","first-page":"1","article-title":"Density modeling of images using a generalized normalization transformation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296792"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451502"},{"key":"ref28","first-page":"1","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref29","first-page":"1","article-title":"Context-adaptive entropy model for end-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6736"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058615"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376704"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_5"},{"key":"ref36","first-page":"1","article-title":"COIN++: Neural compression across modalities","volume":"11","author":"Dupont","year":"2022","journal-title":"IEEE Trans. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613834"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2025.3584291"},{"key":"ref40","first-page":"2922","article-title":"Real-time adaptive image compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rippel"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093415"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412185"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00187"},{"key":"ref45","article-title":"Image compression with product quantized masked image modeling","author":"El-Nouby","year":"2022","journal-title":"arXiv:2212.07372"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00414"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00028"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01533"},{"key":"ref50","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","first-page":"1","article-title":"Solving diffusion ODEs with optimal boundary conditions for better image super-resolution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110799"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"ref56","first-page":"1","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Careil"},{"key":"ref57","article-title":"CMC-bench: Towards a new paradigm of visual signal compression","author":"Li","year":"2024","journal-title":"arXiv:2406.09356"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref59","article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","author":"Wang","year":"2023","journal-title":"arXiv:2309.02773"},{"key":"ref60","article-title":"Lossy compression with Gaussian diffusion","author":"Theis","year":"2022","journal-title":"arXiv:2206.08889"},{"key":"ref61","first-page":"1","article-title":"Correcting diffusion-based perceptual image compression with privileged end-to-end decoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref62","article-title":"High-fidelity image compression with score-based generative models","author":"Hoogeboom","year":"2023","journal-title":"arXiv:2305.18231"},{"key":"ref63","volume-title":"Neural Image Compression With a Diffusion-Based Decoder","author":"Ghouse","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3578127"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551780"},{"key":"ref67","article-title":"MISC: Ultra-low bitrate image semantic compression driven by large multimodal model","author":"Li","year":"2024","journal-title":"arXiv:2402.16749"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"ref70","article-title":"Learning a coarse-to-fine diffusion transformer for image restoration","author":"Wang","year":"2023","journal-title":"arXiv:2308.08730"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401872"},{"key":"ref74","volume-title":"Kodak Lossless True Color Image Suite","author":"Kodak","year":"2024"},{"key":"ref75","article-title":"Workshop and challenge on learned image compression","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Toderici"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref77","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref80","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref81","volume-title":"Calculation of Average PSNR Differences Between RD Curves","author":"Gisle","year":"2001"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2024.10810316"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11333373.pdf?arnumber=11333373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:56:09Z","timestamp":1778183769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":82,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3651547","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}