{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T15:08:04Z","timestamp":1789571284583,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225112, 62271312, 62301310, 623B2073, 62471290"],"award-info":[{"award-number":["62225112, 62271312, 62301310, 623B2073, 62471290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC142"],"award-info":[{"award-number":["2024NSFSC142"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758239","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12934-12941","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards a New Paradigm of Visual Signal Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0634-1710","authenticated-orcid":false,"given":"Chunyi","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4578-2880","authenticated-orcid":false,"given":"Xiele","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-8101","authenticated-orcid":false,"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8984-0425","authenticated-orcid":false,"given":"Donghui","family":"Feng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. showeprint2308.12966"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 675-685","author":"Blau Yochai","year":"2019","unstructured":"Yochai Blau and Tomer Michaeli. 2019. Rethinking lossy compression: The rate-distortion-perception tradeoff. In International Conference on Machine Learning. PMLR, 675-685."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"e_1_3_2_1_9_1","unstructured":"Junsong Chen Jincheng Yu Chongjian Ge Lewei Yao Enze Xie Yue Wu Zhongdao Wang James Kwok Ping Luo Huchuan Lu and Zhenguo Li. 2023b. PixArt-\u03b1: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. showeprint2310.00426"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Lin Chen Jisong Li Xiaoyi Dong Pan Zhang Conghui He Jiaqi Wang Feng Zhao and Dahua Lin. 2023a. ShareGPT4V: Improving Large Multi-Modal Models with Better Captions. showeprint2311.12793","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"e_1_3_2_1_12_1","unstructured":"Civital. 2024. RealVisXL-V4.0. https:\/\/realvis.art\/."},{"key":"e_1_3_2_1_13_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. showeprint2305.06500"},{"key":"e_1_3_2_1_14_1","volume-title":"Image quality assessment: Unifying structure and texture similarity","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 transactions on pattern analysis and machine intelligence, Vol. 44, 5 (2020), 2567-2581."},{"key":"e_1_3_2_1_15_1","unstructured":"dreamlike art. 2023. dreamlike-photoreal-2.0. https:\/\/dreamlike.art."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130754"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3364153"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310657"},{"key":"e_1_3_2_1_19_1","volume-title":"NTIRE 2022 challenge on perceptual image quality assessment. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 951-967","author":"Gu Jinjin","year":"2022","unstructured":"Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S Ren, Radu Timofte, Yuan Gong, Shanshan Lao, Shuwei Shi, Jiahao Wang, Sidi Yang, et al., 2022. NTIRE 2022 challenge on perceptual image quality assessment. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 951-967."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_21_1","unstructured":"Yatharth Gupta Vishnu V. Jaddipal Harish Prabhala Sayak Paul and Patrick Von Platen. 2024. Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss. showeprint2401.02677"},{"key":"e_1_3_2_1_22_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing 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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_23_1","unstructured":"David Holz. 2023. Midjourney. https:\/\/www.midjourney.com."},{"key":"e_1_3_2_1_24_1","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume":"36","author":"Huang Kaiyi","year":"2023","unstructured":"Kaiyi Huang, Kaiyue Sun, Enze Xie, Zhenguo Li, and Xihui Liu. 2023. T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 78723-78747.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_26_1","unstructured":"Tengchuan Kou Xiaohong Liu Zicheng Zhang Chunyi Li Haoning Wu Xiongkuo Min Guangtao Zhai and Ning Liu. 2024. Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment. arXiv:2403.11956"},{"key":"e_1_3_2_1_27_1","unstructured":"Shanshan Lao Yuan Gong Shuwei Shi Sidi Yang Tianhe Wu Jiahao Wang Weihao Xia and Yujiu Yang. 2022. Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network. showeprint2204.10485"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"e_1_3_2_1_29_1","volume-title":"Text Sketch: Image Compression at Ultra Low Rates. arXiv:2307.01944 [cs.LG]","author":"Lei Eric","year":"2023","unstructured":"Eric Lei, Yi?it Berkay Uslu, Hamed Hassani, and Shirin Saeedi Bidokhti. 2023. Text Sketch: Image Compression at Ultra Low Rates. arXiv:2307.01944 [cs.LG]"},{"key":"e_1_3_2_1_30_1","unstructured":"Anqi Li Yuxi Liu Huihui Bai Feng Li Runmin Cong Meng Wang and Yao Zhao. 2024c. Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption. arXiv:2406.00758"},{"key":"e_1_3_2_1_31_1","unstructured":"Bohao Li Rui Wang Guangzhi Wang Yuying Ge Yixiao Ge and Ying Shan. 2023a. SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension. showeprint2307.16125"},{"key":"e_1_3_2_1_32_1","unstructured":"Chunyi Li Tengchuan Kou Yixuan Gao Yuqin Cao Wei Sun Zicheng Zhang Yingjie Zhou Zhichao Zhang Weixia Zhang Haoning Wu Xiaohong Liu Xiongkuo Min and Guangtao Zhai. 2024b. AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment. showeprint2404.03407"},{"key":"e_1_3_2_1_33_1","volume-title":"2024 e","author":"Li Chunyi","unstructured":"Chunyi Li, Guo Lu, Donghui Feng, Haoning Wu, Zicheng Zhang, Xiaohong Liu, Guangtao Zhai, Weisi Lin, and Wenjun Zhang. 2024 e. MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model. showeprint2402.16749"},{"key":"e_1_3_2_1_34_1","unstructured":"Chunyi Li Haoning Wu Hongkun Hao Zicheng Zhang Tengchaun Kou Chaofeng Chen Lei Bai Xiaohong Liu Weisi Lin and Guangtao Zhai. 2024 f. G-Refine: A General Quality Refiner for Text-to-Image Generation. showeprint2404.18343"},{"key":"e_1_3_2_1_35_1","unstructured":"Chunyi Li Haoning Wu Zicheng Zhang Hongkun Hao Kaiwei Zhang Lei Bai Xiaohong Liu Xiongkuo Min Weisi Lin and Guangtao Zhai. 2024 g. Q-Refine: A Perceptual Quality Refiner for AI-Generated Image. showeprint2401.01117"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949270"},{"key":"e_1_3_2_1_37_1","volume-title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","author":"Li Chunyi","year":"2023","unstructured":"Chunyi Li, Zicheng Zhang, Haoning Wu, Wei Sun, Xiongkuo Min, Xiaohong Liu, Guangtao Zhai, and Weisi Lin. 2023b. AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"Daiqing Li Aleks Kamko Ehsan Akhgari Ali Sabet Linmiao Xu and Suhail Doshi. 2024a. Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation. showeprint2402.17245"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475558"},{"key":"e_1_3_2_1_40_1","unstructured":"Yixuan Li Xuelin Liu Xiaoyang Wang Shiqi Wang and Weisi Lin. 2024d. FakeBench: Uncover the Achilles' Heels of Fake Images with Large Multimodal Models. showeprint2404.13306"},{"key":"e_1_3_2_1_41_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Xinqi Lin Jingwen He Ziyan Chen Zhaoyang Lyu Bo Dai Fanghua Yu Wanli Ouyang Yu Qiao and Chao Dong. 2024. DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior. showeprint2308.15070","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3175023"},{"key":"e_1_3_2_1_44_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023b. Visual Instruction Tuning. showeprint2304.08485"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00637"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yuan Liu Haodong Duan Yuanhan Zhang Bo Li Songyang Zhang Wangbo Zhao Yike Yuan Jiaqi Wang Conghui He Ziwei Liu Kai Chen and Dahua Lin. 2024a. MMBench: Is Your Multi-modal Model an All-around Player? showeprint2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00028"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2735192"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2718185"},{"key":"e_1_3_2_1_50_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_51_1","unstructured":"PlaygroundAI. 2023. playground-v2-1024px-aesthetic. https:\/\/playground.com."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"e_1_3_2_1_53_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_54_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv:2204.06125 [cs.CV]"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_56_1","unstructured":"Robin Rombach Andreas Blattmann and Bj\u00f6rn Ommer. 2022a. Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models. arXiv:2207.13038 [cs.CV]"},{"key":"e_1_3_2_1_57_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_58_1","first-page":"33","volume-title":"Zurich","author":"Shen Chengyao","year":"2014","unstructured":"Chengyao Shen and Qi Zhao. 2014. Webpage saliency. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII 13. Springer, 33-46."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_63_1","unstructured":"Jianyi Wang Zongsheng Yue Shangchen Zhou Kelvin C. K. Chan and Chen Change Loy. 2023b. Exploiting Diffusion Prior for Real-World Image Super-Resolution. showeprint2305.07015"},{"key":"e_1_3_2_1_64_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_1_66_1","unstructured":"Haoning Wu Zicheng Zhang Erli Zhang Chaofeng Chen Liang Liao Annan Wang Chunyi Li Wenxiu Sun Qiong Yan Guangtao Zhai and Weisi Lin. 2024. Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision. showeprint2309.14181"},{"key":"e_1_3_2_1_67_1","volume-title":"Q-instruct: Improving low-level visual abilities for multi-modality foundation models. showeprint2311.06783","author":"Wu Haoning","year":"2023","unstructured":"Haoning Wu, Zicheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Kaixin Xu, Chunyi Li, Jingwen Hou, Guangtao Zhai, et al., 2023c. Q-instruct: Improving low-level visual abilities for multi-modality foundation models. showeprint2311.06783"},{"key":"e_1_3_2_1_68_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Liang Liao Chunyi Li Yixuan Gao Annan Wang Erli Zhang Wenxiu Sun et al. 2023b. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. showeprint2312.17090"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169055"},{"key":"e_1_3_2_1_70_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2024. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Naifu Xue Qi Mao Zijian Wang Yuan Zhang and Siwei Ma. 2024. Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer. showeprint2403.03736","DOI":"10.1109\/ICME57554.2024.10687549"},{"key":"e_1_3_2_1_72_1","first-page":"64971","volume-title":"Levine (Eds.)","volume":"36","author":"Yang Ruihan","year":"2023","unstructured":"Ruihan Yang and Stephan Mandt. 2023. Lossy Image Compression with Conditional Diffusion Models. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 64971-64995."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","unstructured":"Tao Yang Rongyuan Wu Peiran Ren Xuansong Xie and Lei Zhang. 2024. Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization. showeprint2308.14469","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"e_1_3_2_1_74_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi Chaoya Jiang Chenliang Li Yuanhong Xu Hehong Chen Junfeng Tian Qian Qi Ji Zhang and Fei Huang. 2023. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. showeprint2304.14178"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"e_1_3_2_1_80_1","first-page":"1","article-title":"Subjective and objective quality assessment for in-the-wild computer graphics images","volume":"20","author":"Zhang Zicheng","year":"2023","unstructured":"Zicheng Zhang, Wei Sun, Yingjie Zhou, Jun Jia, Zhichao Zhang, Jing Liu, Xiongkuo Min, and Guangtao Zhai. 2023c. Subjective and objective quality assessment for in-the-wild computer graphics images. ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 20, 4 (2023), 1-22.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_81_1","unstructured":"Zicheng Zhang Haoning Wu Chunyi Li Yingjie Zhou Wei Sun Xiongkuo Min Zijian Chen Xiaohong Liu Weisi Lin and Guangtao Zhai. 2024. A-Bench: Are LMMs Masters at Evaluating AI-generated Images? arXiv:2406.03070"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:01:03Z","timestamp":1765342863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":81,"alternative-id":["10.1145\/3746027.3758239","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758239","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}