{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:01Z","timestamp":1777865281203,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01787","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19227-19236","source":"Crossref","is-referenced-by-count":0,"title":["DLF: Extreme Image Compression with Dual-Generative Latent Fusion"],"prefix":"10.1109","author":[{"given":"Naifu","family":"Xue","sequence":"first","affiliation":[{"name":"Communication University of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Jia","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","volume-title":"Dataset","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.150"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref4","article-title":"Calculation of average psnr differences between rd-curves","author":"Bjontegaard","year":"2001","journal-title":"ITU SG16 Doc. VCEG-M33"},{"key":"ref5","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"In Proceedings of the 36th International Conference on Machine Learning","author":"Blau"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref7","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Careil"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2971765"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","author":"Franzen","year":"1999","journal-title":"Kodak PhotoCD dataset"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"In Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611694"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3708347"},{"key":"ref19","author":"K\u00f6rber","year":"2024","journal-title":"Perco (sd): Open perceptual compression"},{"key":"ref20","author":"Lee","year":"2024","journal-title":"Neural image compression with text-guided encoding for both pixel-level and perceptual fidelity"},{"key":"ref21","author":"Lei","year":"2023","journal-title":"Text + sketch: Image compression at ultra low rates"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3455576"},{"key":"ref25","author":"Li","year":"2024","journal-title":"Diffusion-based extreme image compression with compressed feature initialization"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00028"},{"key":"ref32","first-page":"11913","article-title":"High-fidelity generative image compression","author":"Mentzer","year":"2020","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref33","author":"Mentzer","year":"2023","journal-title":"Finite scalar quantization: Vq-vae made simple"},{"key":"ref34","first-page":"25426","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"In Proceedings of the 40th International Conference on Machine Learning","author":"Muckley"},{"key":"ref35","author":"Pernias","year":"2023","journal-title":"Wuerstchen: An efficient architecture for large-scale text-to-image diffusion models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3571944"},{"key":"ref37","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref38","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref40","author":"Toderici","year":"2020","journal-title":"Workshop and challenge on learned image compression (clic 2020)"},{"key":"ref41","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Evc: Towards real-time neural image compression with mask decay","volume-title":"In International Conference on Learning Representations","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref44","article-title":"Idempotence and perceptual image compression","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02648"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687549"},{"key":"ref47","article-title":"One-step diffusion-based image compression with semantic distillation","author":"Xue","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2835"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref50","article-title":"Spae: Semantic pyramid autoencoder for multimodal generation with frozen 11 ms","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","author":"Yu","year":"2024","journal-title":"An image is worth 32 tokens for reconstruction and generation"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01614"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00210"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3580499"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443337.pdf?arnumber=11443337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:17Z","timestamp":1777529417000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01787","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}