{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:40:45Z","timestamp":1755826845023,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,10]]},"DOI":"10.1145\/3610548.3618230","type":"proceedings-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T12:28:40Z","timestamp":1702297720000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Animating Street View"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1520-5979","authenticated-orcid":false,"given":"Mengyi","family":"Shan","sequence":"first","affiliation":[{"name":"University of Washington, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0095-5400","authenticated-orcid":false,"given":"Brian","family":"Curless","sequence":"additional","affiliation":[{"name":"University of Washington, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9498-584X","authenticated-orcid":false,"given":"Ira","family":"Kemelmacher-Shlizerman","sequence":"additional","affiliation":[{"name":"University of Washington, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4214-4078","authenticated-orcid":false,"given":"Steve","family":"Seitz","sequence":"additional","affiliation":[{"name":"University of Washington, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01336-9"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4008\u20134017","author":"Bhat Farooq","key":"e_1_3_2_2_2_1","unstructured":"S.\u00a0Farooq Bhat, I. Alhashim, and P. Wonka. 2021. AdaBins: Depth Estimation Using Adaptive Bins. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4008\u20134017."},{"volume-title":"SIGGRAPH Asia Posters (Tokyo, Japan)","author":"Chang Shih-Hsiu","key":"e_1_3_2_2_3_1","unstructured":"Shih-Hsiu Chang, Ching-Ya Chiu, Chia-Sheng Chang, Kuo-Wei Chen, Chih-Yuan Yao, Ruen-Rone Lee, and Hung-Kuo Chu. 2018. Generating 360 Outdoor Panorama Dataset with Reliable Sun Position Estimation. In SIGGRAPH Asia Posters (Tokyo, Japan). Association for Computing Machinery, New York, NY, USA, Article 22, 2\u00a0pages."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"e_1_3_2_2_5_1","volume-title":"Detecting Nonexistent Pedestrians. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW).","author":"Chien Jui-Ting","year":"2017","unstructured":"Jui-Ting Chien, Chia-Jung Chou, Ding-Jie Chen, and Hwann-Tzong Chen. 2017. Detecting Nonexistent Pedestrians. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_5"},{"key":"e_1_3_2_2_8_1","volume-title":"BlobGAN: Spatially Disentangled Scene Representations. European Conference on Computer Vision (ECCV)","author":"Epstein Dave","year":"2022","unstructured":"Dave Epstein, Taesung Park, Richard Zhang, Eli Shechtman, and Alexei\u00a0A. Efros. 2022. BlobGAN: Spatially Disentangled Scene Representations. European Conference on Computer Vision (ECCV) (2022)."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 770\u2013778","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 770\u2013778."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00709"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00575"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19974"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Yangyi Huang Hongwei Yi Weiyang Liu Haofan Wang Boxi Wu Wenxiao Wang Binbin Lin Debing Zhang and Deng Cai. 2022a. One-shot Implicit Animatable Avatars with Model-based Priors. arxiv:arXiv:2212.02469","DOI":"10.1109\/ICCV51070.2023.00824"},{"key":"e_1_3_2_2_15_1","unstructured":"Ziyuan Huang Zhengping Zhou Yung-Yu Chuang Jiajun Wu and C.\u00a0Karen Liu. 2022b. Physically Plausible Animation of Human Upper Body from a Single Image. arxiv:2212.04741"},{"key":"e_1_3_2_2_16_1","volume-title":"Unity: A General Platform for Intelligent Agents. arxiv:1809.02627","author":"Juliani Arthur","year":"2018","unstructured":"Arthur Juliani, Vincent-Pierre Berges, Esh Vckay, Yuan Gao, Hunter Henry, Marwan Mattar, and Danny Lange. 2018. Unity: A General Platform for Intelligent Agents. arxiv:1809.02627"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Johanna Karras Aleksander Holynski Ting-Chun Wang and Ira Kemelmacher-Shlizerman. 2023. DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion. arxiv:arXiv:2304.06025","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024191"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2602146"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 10414\u201310424","author":"Lee Donghoon","year":"2018","unstructured":"Donghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, and Jan Kautz. 2018. Context-Aware Synthesis and Placement of Object Instances. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS). 10414\u201310424."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01030"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00985"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00816"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation (ICRA). 6292\u20136299","author":"Ma Wei-Chiu","year":"2016","unstructured":"Wei-Chiu Ma, Shenlong Wang, Marcus\u00a0A. Brubaker, Sanja Fidler, and Raquel Urtasun. 2016. Find your way by observing the sun and other semantic cues. In Proceedings of IEEE International Conference on Robotics and Automation (ICRA). 6292\u20136299."},{"key":"e_1_3_2_2_27_1","volume-title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance. arxiv:2302.13153","author":"Ma Duo\u00a0Kurt","year":"2023","unstructured":"Wan-Duo\u00a0Kurt Ma, J.\u00a0P. Lewis, W.\u00a0Bastiaan Kleijn, and Thomas Leung. 2023. Directed Diffusion: Direct Control of Object Placement through Attention Guidance. arxiv:2302.13153"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS).","author":"Mallya Arun","year":"2022","unstructured":"Arun Mallya, Ting-Chun Wang, and Ming-Yu Liu. 2022. Implicit Warping for Animation with Image Sets. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00357"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00993"},{"key":"e_1_3_2_2_31_1","unstructured":"Thu Nguyen-Phuoc Christian Richardt Long Mai Yong-Liang Yang and Niloy Mitra. 2020. BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images. In Advances in Neural Information Processing Systems 33."},{"key":"e_1_3_2_2_32_1","unstructured":"Haomiao Ni Changhao Shi Kai Li Sharon\u00a0X. Huang and Martin\u00a0Renqiang Min. 2023. Conditional Image-to-Video Generation with Latent Flow Diffusion Models. arxiv:2303.13744"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02062.x"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"volume-title":"Poisson image editing","author":"P\u00e9rez Patrick","key":"e_1_3_2_2_36_1","unstructured":"Patrick P\u00e9rez, Michel Gangnet, and Andrew Blake. 2003. Poisson image editing. In ACM SIGGRAPH. Association for Computing Machinery, New York, NY, USA, 313\u2013318."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"A. Pumarola A. Agudo A.M. Martinez A. Sanfeliu and F. Moreno-Noguer. 2019. GANimation: One-Shot Anatomically Consistent Facial Animation. International Journal of Computer Vision (IJCV) (2019).","DOI":"10.1007\/s11263-019-01210-3"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_39_1","unstructured":"Yizhi Song Zhifei Zhang Zhe Lin Scott Cohen Brian Price Jianming Zhang Soo\u00a0Ye Kim and Daniel Aliaga. 2022. ObjectStitch: Generative Object Compositing. arxiv:2212.00932"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_12"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_26"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142008"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.412624"},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS).","author":"Wang Ting-Chun","year":"2019","unstructured":"Ting-Chun Wang, Ming-Yu Liu, Andrew Tao, Guilin Liu, Jan Kautz, and Bryan Catanzaro. 2019. Few-shot Video-to-Video Synthesis. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_26"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00507"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_22"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00606"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of Neural Information Processing Systems (NeurIPS).","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose\u00a0M Alvarez, and Ping Luo. 2021. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. In Proceedings of Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_50_1","unstructured":"Yinghao Xu Menglei Chai Zifan Shi Sida Peng Skorokhodov Ivan Siarohin Aliaksandr Ceyuan Yang Yujun Shen Hsin-Ying Lee Bolei Zhou and Tulyakov Sergy. 2022. DiscoScene: Spatially Disentangled Generative Radiance Field for Controllable 3D-aware Scene Synthesis. arxiv:2212.11984"},{"key":"e_1_3_2_2_51_1","volume-title":"GIRAFFE HD: A High-Resolution 3D-aware Generative Model. In CVPR.","author":"Xue Yang","year":"2022","unstructured":"Yang Xue, Yuheng Li, Krishna\u00a0Kumar Singh, and Yong\u00a0Jae Lee. 2022. GIRAFFE HD: A High-Resolution 3D-aware Generative Model. In CVPR."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01479"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00359"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00377"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480500"},{"key":"e_1_3_2_2_56_1","volume-title":"Learning Physically Simulated Tennis Skills from Broadcast Videos. ACM Transactions on Graphics (TOG)","author":"Zhang Haotian","year":"2023","unstructured":"Haotian Zhang, Ye Yuan, Viktor Makoviychuk, Yunrong Guo, Sanja Fidler, Xue\u00a0Bin Peng, and Kayvon Fatahalian. 2023. Learning Physically Simulated Tennis Skills from Broadcast Videos. ACM Transactions on Graphics (TOG) (2023), 1\u201316."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00466"}],"event":{"name":"SA '23: SIGGRAPH Asia 2023","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Sydney NSW Australia","acronym":"SA '23"},"container-title":["SIGGRAPH Asia 2023 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610548.3618230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:30:38Z","timestamp":1755768638000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610548.3618230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":57,"alternative-id":["10.1145\/3610548.3618230","10.1145\/3610548"],"URL":"https:\/\/doi.org\/10.1145\/3610548.3618230","relation":{},"subject":[],"published":{"date-parts":[[2023,12,10]]},"assertion":[{"value":"2023-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}