{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T19:09:14Z","timestamp":1762110554761,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National R&D project of China","award":["2021YFC3340304"],"award-info":[{"award-number":["2021YFC3340304"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681336","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"1622-1631","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression"],"prefix":"10.1145","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, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7210-4018","authenticated-orcid":false,"given":"Yiyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1692-0069","authenticated-orcid":false,"given":"Wenhan","family":"Yang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4944-9621","authenticated-orcid":false,"given":"Zongming","family":"Guo","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China"}]},{"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"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"NTIRE 2017 challenge on single image super-resolution: dataset and study. In Proc. IEEE\/CVF Int'l Conf. Comput. Vision and Pattern Recognit.","author":"Agustsson Eirikur","year":"2017","unstructured":"Eirikur Agustsson and Radu Timofte. 2017. NTIRE 2017 challenge on single image super-resolution: dataset and study. In Proc. IEEE\/CVF Int'l Conf. Comput. Vision and Pattern Recognit."},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Ball\u00e9 Johannes","year":"2016","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P Simoncelli. 2016. Density modeling of images using a generalized normalization transformation. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Ball\u00e9 Johannes","year":"2017","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P Simoncelli. 2017. End-to-end optimized image compression. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Ball\u00e9 Johannes","year":"2019","unstructured":"Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2019. Variational image compression with a scale hyperprior. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_5_1","unstructured":"Fabrice Bellard. 2017. BPG image format. http:\/\/bellard.org\/bpg\/"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. Int'l Conf. Mach. Learn.","author":"Blau Yochai","year":"2019","unstructured":"Yochai Blau and Tomer Michaeli. 2019. Rethinking lossy compression: The rate-distortion-perception tradeoff. In Proc. Int'l Conf. Mach. Learn."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613834"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058615"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_11_1","first-page":"2567","article-title":"Image quality assessment: Unifying structure and texture similarity","volume":"44","author":"Ding Keyan","year":"2020","unstructured":"Keyan Ding, Kede Ma, Shiqi Wang, and Eero P Simoncelli. 2020. Image quality assessment: Unifying structure and texture similarity. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 44, 5 (2020), 2567--2581.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Dinh Laurent","year":"2016","unstructured":"Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. 2016. Density estimation using real NVP. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Du Yilun","year":"2019","unstructured":"Yilun Du and Igor Mordatch. 2019. Implicit generation and modeling with energy based models. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_14_1","volume-title":"Yee Whye Teh, and Arnaud Doucet","author":"Dupont Emilien","year":"2022","unstructured":"Emilien Dupont, Hrushikesh Loya, Milad Alizadeh, Adam Goli'nski, Yee Whye Teh, and Arnaud Doucet. 2022. COIN: Neural compression across modalities. IEEE Trans. Mach. Learn. Res. (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00958"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. Int'l Conf. Mach. Learn.","author":"Germain Mathieu","year":"2015","unstructured":"Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle. 2015. MADE: Masked autoencoder for distribution estimation. In Proc. Int'l Conf. Mach. Learn."},{"key":"e_1_3_2_1_18_1","unstructured":"Noor Fathima Khanum Mohamed Ghouse Jens Petersen Auke J. Wiggers Tianlin Xu and Guillaume Sautiere. 2023. Neural Image Compression with a Diffusion-based Decoder. https:\/\/openreview.net\/forum?id=4Jq0XWCZQel"},{"key":"e_1_3_2_1_19_1","unstructured":"Bj\u00f8ntegaard Gisle. 2001. Calculation of average PSNR differences between RD curves. In VCEG-M33. https:\/\/api.semanticscholar.org\/CorpusID:61598325"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00187"},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_25_1","volume-title":"High-fidelity image compression with score-based generative models. arXiv preprint arXiv:2305.18231","author":"Hoogeboom Emiel","year":"2023","unstructured":"Emiel Hoogeboom, Eirikur Agustsson, Fabian Mentzer, Luca Versari, George Toderici, and Lucas Theis. 2023. High-fidelity image compression with score-based generative models. arXiv preprint arXiv:2305.18231 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6736"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611694"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_30_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik Pieter","year":"2014","unstructured":"Diederik Pieter Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Kingma Durk P","year":"2018","unstructured":"Durk P Kingma and Prafulla Dhariwal. 2018. Glow: Generative flow with invertible 1x1 convolutions. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Max Welling. 2014. Auto-encoding variational Bayes. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_33_1","unstructured":"Eastman Kodak. 2024. Kodak lossless true color image suite. https:\/\/r0k.us\/graphics\/kodak\/"},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. Int'l Conf. Mach. Learn.","author":"Kusner Matt J","year":"2017","unstructured":"Matt J Kusner, Brooks Paige, and Jos\u00e9 Miguel Hern\u00e1ndez-Lobato. 2017. Grammar variational autoencoder. In Proc. Int'l Conf. Mach. Learn."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01243"},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Lee Jooyoung","year":"2018","unstructured":"Jooyoung Lee, Seunghyun Cho, and Seung-Kwon Beack. 2018. Context-adaptive entropy model for end-to-end optimized image compression. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007828"},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_27"},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Ma Yiyang","year":"2024","unstructured":"Yiyang Ma, Huan Yang, Wenhan Yang, Jianlong Fu, and Jiaying Liu. 2024. Solving diffusion ODEs with optimal boundary conditions for better image super-resolution. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2000.838192"},{"key":"e_1_3_2_1_43_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Mentzer Fabian","year":"2020","unstructured":"Fabian Mentzer, George Toderici, Michael Tschannen, and Eirikur Agustsson. 2020. High-fidelity generative image compression. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296792"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451502"},{"key":"e_1_3_2_1_46_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_47_1","volume-title":"Proc. Int'l Conf. Mach. Learn.","author":"Muckley Matthew","year":"2023","unstructured":"Matthew Muckley, Alaaeldin El-Nouby, Karen Ullrich, Herv\u00e9 J\u00e9gou, and Jakob Verbeek. 2023. Improving statistical fidelity for neural image compression with implicit local likelihood models. In Proc. Int'l Conf. Mach. Learn."},{"key":"e_1_3_2_1_48_1","volume-title":"Denoising diffusion post-processing for low-light image enhancement. arXiv preprint arXiv:2303.09627","author":"Panagiotou Savvas","year":"2023","unstructured":"Savvas Panagiotou and Anna S Bosman. 2023. Denoising diffusion post-processing for low-light image enhancement. arXiv preprint arXiv:2303.09627 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_50_1","first-page":"4713","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi. 2022. Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell., Vol. 45, 4 (2022), 4713--4726.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"e_1_3_2_1_52_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising diffusion implicit models. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_54_1","volume-title":"Proc. Int'l Conf. Learn. Representations.","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. In Proc. Int'l Conf. Learn. Representations."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_5"},{"key":"e_1_3_2_1_56_1","volume-title":"Workshop and challenge on learned image compression. In Proc. IEEE\/CVF Int'l Conf. Comput. Vision and Pattern Recognit. Workshop.","author":"Toderici George","year":"2020","unstructured":"George Toderici, Wenzhe Shi, Radu Timofte, Lucas Theis, Johannes Balle, Eirikur Agustsson, Nick Johnston, and Fabian Mentzer. 2020. Workshop and challenge on learned image compression. In Proc. IEEE\/CVF Int'l Conf. Comput. Vision and Pattern Recognit. Workshop."},{"key":"e_1_3_2_1_57_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01686"},{"key":"e_1_3_2_1_60_1","volume-title":"Learning a coarse-to-fine diffusion transformer for image restoration. arXiv preprint arXiv:2308.08730","author":"Wang Liyan","year":"2023","unstructured":"Liyan Wang, Qinyu Yang, Cong Wang, Wei Wang, Jinshan Pan, and Zhixun Su. 2023. Learning a coarse-to-fine diffusion transformer for image restoration. arXiv preprint arXiv:2308.08730 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_1_62_1","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems.","author":"Yang Ruihan","year":"2023","unstructured":"Ruihan Yang and Stephan Mandt. 2023. Lossy image compression with conditional diffusion models. In Proc. Annu. Conf. Neural Inf. Process. Systems."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3261268"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681336","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:43Z","timestamp":1750295863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":66,"alternative-id":["10.1145\/3664647.3681336","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681336","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}