{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:54Z","timestamp":1781539074678,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810849","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"835-844","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8439-8903","authenticated-orcid":false,"given":"Jiagao","family":"Hu","sequence":"first","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9351-2067","authenticated-orcid":false,"given":"Daiguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2259-9171","authenticated-orcid":false,"given":"Danzhen","family":"Fu","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4830-2171","authenticated-orcid":false,"given":"Fuhao","family":"Li","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2366-8455","authenticated-orcid":false,"given":"Zepeng","family":"Wang","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5698-396X","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9422-9484","authenticated-orcid":false,"given":"Wenhua","family":"Liao","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6586-219X","authenticated-orcid":false,"given":"Jiayi","family":"Xie","sequence":"additional","affiliation":[{"name":"MiLM Plus, Xiaomi Inc., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5252-0696","authenticated-orcid":false,"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiaomi EV, Shaighai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_3_2_3_2","unstructured":"Liang-Chieh Chen George Papandreou Florian Schroff and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.05587 (2017)."},{"key":"e_1_3_3_2_4_2","unstructured":"Rui Chen Zehuan Wu Yichen Liu Yuxin Guo Jingcheng Ni Haifeng Xia and Siyu Xia. 2024. Unimlvg: Unified framework for multi-view long video generation with comprehensive control capabilities for autonomous driving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04842 (2024)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_2_6_2","unstructured":"Ruiyuan Gao Kai Chen Bo Xiao Lanqing Hong Zhenguo Li and Qiang Xu. 2025. MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control. (2025)."},{"key":"e_1_3_3_2_7_2","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Gao Ruiyuan","year":"2023","unstructured":"Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, and Qiang Xu. 2023. Magicdrive: Street view generation with diverse 3d geometry control. In The Eleventh International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_3_2_8_2","unstructured":"Shenyuan Gao Jiazhi Yang Li Chen Kashyap Chitta Yihang Qiu Andreas Geiger Jun Zhang and Hongyang Li. 2024. Vista: A generalizable driving world model with high fidelity and versatile controllability. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17398 (2024)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02087"},{"key":"e_1_3_3_2_10_2","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 30 (2017)."},{"key":"e_1_3_3_2_11_2","unstructured":"Junpeng Jiang Gangyi Hong Lijun Zhou Enhui Ma Hengtong Hu Xia Zhou Jie Xiang Fan Liu Kaicheng Yu Haiyang Sun et\u00a0al. 2024. Dive: Dit-based video generation with enhanced control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.01595 (2024)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.396"},{"key":"e_1_3_3_2_14_2","unstructured":"Gongjin Lan Yang Peng Qi Hao and Chengzhong Xu. 2024. Sustechgan: Image generation for object detection in adverse conditions of autonomous driving. IEEE Transactions on Intelligent Vehicles (2024)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00173"},{"key":"e_1_3_3_2_16_2","unstructured":"Xuelong Li Chen Li Kai Kou and Bin Zhao. 2022. Weather translation via weather-cue transferring. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_3_2_17_2","unstructured":"Chih-Hao Lin Zian Wang Ruofan Liang Yuxuan Zhang Sanja Fidler Shenlong Wang and Zan Gojcic. 2025. Controllable Weather Synthesis and Removal with Video Diffusion Models. IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_2_19_2","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Lipman Yaron","year":"2023","unstructured":"Yaron Lipman, Ricky\u00a0TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matthew Le. 2023. Flow Matching for Generative Modeling. In The Eleventh International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Yun-Fu Liu Da-Wei Jaw Shih-Chia Huang and Jenq-Neng Hwang. 2018. Desnownet: Context-aware deep network for snow removal. IEEE Transactions on Image Processing 27 6 (2018) 3064\u20133073.","DOI":"10.1109\/TIP.2018.2806202"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_23_2","unstructured":"Chaojun Ni Guosheng Zhao Xiaofeng Wang Zheng Zhu Wenkang Qin Guan Huang Chen Liu Yuyin Chen Yida Wang Xueyang Zhang et\u00a0al. 2024. ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.19548 (2024)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02085"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00626"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Ozan \u00d6zdenizci and Robert Legenstein. 2023. Restoring vision in adverse weather conditions with patch-based denoising diffusion models. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 8 (2023) 10346\u201310357.","DOI":"10.1109\/TPAMI.2023.3238179"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01298"},{"key":"e_1_3_3_2_28_2","unstructured":"Chenghao Qian Wenjing Li Yuhu Guo and Gustav Markkula. 2025. WeatherEdit: Controllable Weather Editing with 4D Gaussian Field. (2025). arxiv:https:\/\/arXiv.org\/abs\/2505.20471\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.20471"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00263"},{"key":"e_1_3_3_2_30_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"e_1_3_3_2_32_2","unstructured":"Yiren Song Cheng Liu and Mike\u00a0Zheng Shou. 2025. Omniconsistency: Learning style-agnostic consistency from paired stylization data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.18445 (2025)."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Zhuo Su Jiehua Zhang Longguang Wang Hua Zhang Zhen Liu Matti Pietik\u00e4inen and Li Liu. 2023. Lightweight pixel difference networks for efficient visual representation learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 12 (2023) 14956\u201314974.","DOI":"10.1109\/TPAMI.2023.3300513"},{"key":"e_1_3_3_2_34_2","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.01717 (2018)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00239"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Lucai Wang Hongda Qin Xuanyu Zhou Xiao Lu and Fengting Zhang. 2023. R-YOLO: A robust object detector in adverse weather. IEEE Transactions on Instrumentation and Measurement 72 (2023) 1\u201311.","DOI":"10.1109\/TIM.2022.3229717"},{"key":"e_1_3_3_2_37_2","first-page":"55","volume-title":"European Conference on Computer Vision","author":"Wang Xiaofeng","year":"2024","unstructured":"Xiaofeng Wang, Zheng Zhu, Guan Huang, Xinze Chen, Jiagang Zhu, and Jiwen Lu. 2024. DriveDreamer: Towards Real-World-Drive World Models for Autonomous Driving. In European Conference on Computer Vision. Springer, 55\u201372."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"e_1_3_3_2_40_2","unstructured":"Wei Wu Xi Guo Weixuan Tang Tingxuan Huang Chiyu Wang Dongyue Chen and Chenjing Ding. 2025. Drivescape: Towards high-resolution controllable multi-view driving video generation. Proceedings of the Computer Vision and Pattern Recognition Conference (2025)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Hanguang Xiao Shihong Liu Kun Zuo Haipeng Xu Yuyang Cai Tianqi Liu and Zhiying Yang. 2024. Multiple adverse weather image restoration: A review. Neurocomputing (2024) 129044.","DOI":"10.1016\/j.neucom.2024.129044"},{"key":"e_1_3_3_2_42_2","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Xie Bin","year":"2025","unstructured":"Bin Xie, Yingfei Liu, Tiancai Wang, Jiale Cao, and Xiangyu Zhang. 2025. Glad: A Streaming Scene Generator for Autonomous Driving. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=ZFxpclrCCf"},{"key":"e_1_3_3_2_43_2","first-page":"156","volume-title":"European Conference on Computer Vision","author":"Yan Yunzhi","year":"2024","unstructured":"Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, and Sida Peng. 2024. Street gaussians: Modeling dynamic urban scenes with gaussian splatting. In European Conference on Computer Vision. Springer, 156\u2013173."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01214"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02419"},{"key":"e_1_3_3_2_47_2","volume-title":"The Thirteenth International Conference on Learning Representations,ICLR 2025, Singapore, April 24-28, 2025","author":"Yang Zhuoyi","year":"2025","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et\u00a0al. 2025. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations,ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Yuxiao Zhang Alexander Carballo Hanting Yang and Kazuya Takeda. 2023. Perception and sensing for autonomous vehicles under adverse weather conditions: A survey. ISPRS Journal of Photogrammetry and Remote Sensing 196 (2023) 146\u2013177.","DOI":"10.1016\/j.isprsjprs.2022.12.021"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Guosheng Zhao Chaojun Ni Xiaofeng Wang Zheng Zhu Xueyang Zhang Yida Wang Guan Huang Xinze Chen Boyuan Wang Youyi Zhang et\u00a0al. 2024. Drivedreamer4d: World models are effective data machines for 4d driving scene representation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.13571 (2024).","DOI":"10.1109\/CVPR52734.2025.01122"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"e_1_3_3_2_53_2","first-page":"270","volume-title":"European Conference on Computer Vision","author":"Zhao Rui","year":"2024","unstructured":"Rui Zhao, Huibin Yan, and Shuoyao Wang. 2024. Revisiting Domain-Adaptive Object Detection in Adverse Weather by the Generation and Composition of High-Quality Pseudo-labels. In European Conference on Computer Vision. Springer, 270\u2013287."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Yunsong Zhou Michael Simon Zhenghao Peng Sicheng Mo Hongzi Zhu Minyi Guo and Bolei Zhou. 2024. Simgen: Simulator-conditioned driving scene generation. Advances in Neural Information Processing Systems 37 (2024) 48838\u201348874.","DOI":"10.52202\/079017-1548"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02083"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:49:34Z","timestamp":1781538574000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":55,"alternative-id":["10.1145\/3805622.3810849","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810849","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}