{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T22:42:09Z","timestamp":1789425729930,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763904","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["In-2-4D: Inbetweening from Two Single-View Images to 4D Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2943-6663","authenticated-orcid":false,"given":"Sauradip","family":"Nag","sequence":"first","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-7445","authenticated-orcid":false,"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[{"name":"Tel Aviv University, Tel Aviv, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1991-119X","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4693-3565","authenticated-orcid":false,"given":"Ali Mahdavi","family":"Amiri","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Alimohammadi Amirhossein","year":"2025","unstructured":"Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari, Andrea Tagliasacchi, Ghassan Hamarneh, and Ali\u00a0Mahdavi Amiri. 2025. SMITE: Segment Me In TimE. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KW6B6s1X82"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"e_1_3_3_2_4_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Ang Cao and Justin Johnson. 2023. HexPlane: A Fast Representation for Dynamic Scenes. CVPR (2023).","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_3_3_2_7_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang Chao Weng and Ying Shan. 2023. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. arxiv:https:\/\/arXiv.org\/abs\/2310.19512\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2310.19512"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657414"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_11_1","volume-title":"2024","author":"Feng Haiwen","year":"2024","unstructured":"Haiwen Feng, Zheng Ding, Zhihao Xia, Simon Niklaus, Victoria Abrevaya, Michael\u00a0J Black, and Xuaner Zhang. 2024. Explorative Inbetweening of Time and Space. In 2024."},{"key":"e_1_3_3_2_12_1","volume-title":"ICLR","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. 2024b. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In ICLR."},{"key":"e_1_3_3_2_13_1","unstructured":"Zhiyang Guo Wen gang Zhou Li Li Min Wang and Houqiang Li. 2024a. Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction. ArXiv abs\/2403.11447 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268512916"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Yanqin Jiang Chaohui Yu Chenjie Cao Fan Wang Weiming Hu and Jin Gao. 2024. Animate3d: Animating any 3d model with multi-view video diffusion. Advances in Neural Information Processing Systems 37 (2024) 125879\u2013125906.","DOI":"10.52202\/079017-3999"},{"key":"e_1_3_3_2_15_1","unstructured":"Yanqin Jiang Li Zhang Jin Gao Weimin Hu and Yao Yao. 2023. Consistent4d: Consistent 360 {\\ deg} dynamic object generation from monocular video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.02848 (2023)."},{"key":"e_1_3_3_2_16_1","unstructured":"Nikita Karaev Ignacio Rocco Benjamin Graham Natalia Neverova Andrea Vedaldi and Christian Rupprecht. 2023. CoTracker: It is Better to Track Together. arXiv:https:\/\/arXiv.org\/abs\/2307.07635 (2023)."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023a. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics 42 4 (July 2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023b. 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics (ToG) 42 4 (2023) 1\u201314.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Levon Khachatryan Andranik Movsisyan Vahram Tadevosyan Roberto Henschel Zhangyang Wang Shant Navasardyan and Humphrey Shi. 2023. Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.13439 (2023).","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Anh\u00a0Cat Le\u00a0Ngo and Raphael C.-W. Phan. 2019. Seeing the Invisible: Survey of Video Motion Magnification and Small Motion Analysis. ACM Comput. Surv. 52 6 (2019).","DOI":"10.1145\/3355389"},{"key":"e_1_3_3_2_21_1","first-page":"12888","volume-title":"International conference on machine learning","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888\u201312900."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Peng Li Yuan Liu Xiaoxiao Long Feihu Zhang Cheng Lin Mengfei Li Xingqun Qi Shanghang Zhang Wei Xue Wenhan Luo et\u00a0al. 2024a. Era3d: high-resolution multiview diffusion using efficient row-wise attention. Advances in Neural Information Processing Systems 37 (2024) 55975\u201356000.","DOI":"10.52202\/079017-1780"},{"key":"e_1_3_3_2_23_1","unstructured":"Ruining Li Chuanxia Zheng Christian Rupprecht and Andrea Vedaldi. 2024b. Puppet-master: Scaling interactive video generation as a motion prior for part-level dynamics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.04631 (2024)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Hanwen Liang Yuyang Yin Dejia Xu Hanxue Liang Zhangyang Wang Konstantinos\u00a0N Plataniotis Yao Zhao and Yunchao Wei. 2024b. Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.16645 (2024).","DOI":"10.52202\/079017-3519"},{"key":"e_1_3_3_2_25_1","unstructured":"Yiqing Liang Numair Khan Zhengqin Li Thu Nguyen-Phuoc Douglas Lanman James Tompkin and Lei Xiao. 2023. GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis. ArXiv abs\/2312.11458 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266359262"},{"key":"e_1_3_3_2_26_1","unstructured":"Yiqing Liang Mikhail Okunev Mikaela\u00a0Angelina Uy Runfeng Li Leonidas Guibas James Tompkin and Adam\u00a0W Harley. 2024a. Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04457 (2024)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Ce Liu Antonio Torralba William\u00a0T. Freeman Fr\u00e9do Durand and Edward\u00a0H. Adelson. 2005. Motion magnification. TOG 24 3 (2005).","DOI":"10.1145\/1073204.1073223"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00410"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01985"},{"key":"e_1_3_3_2_33_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Jia Qin Youyi Zheng and Kun Zhou. 2022. Motion In-Betweening via Two-Stage Transformers. ACM Transactions on Graphics 41 (2022). Issue 6.","DOI":"10.1145\/3550454.3555454"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"e_1_3_3_2_36_1","unstructured":"Jiawei Ren Liang Pan Jiaxiang Tang Chi Zhang Ang Cao Gang Zeng and Ziwei Liu. 2023. DreamGaussian4D: Generative 4D Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17142 (2023)."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"crossref","unstructured":"Jiawei Ren Cheng Xie Ashkan Mirzaei Karsten Kreis Ziwei Liu Antonio Torralba Sanja Fidler Seung\u00a0Wook Kim Huan Ling et\u00a0al. 2025. L4gm: Large 4d gaussian reconstruction model. Advances in Neural Information Processing Systems 37 (2025) 56828\u201356858.","DOI":"10.52202\/079017-1810"},{"key":"e_1_3_3_2_38_1","first-page":"336","volume-title":"European Conference on Computer Vision","author":"Shen Liao","year":"2024","unstructured":"Liao Shen, Tianqi Liu, Huiqiang Sun, Xinyi Ye, Baopu Li, Jianming Zhang, and Zhiguo Cao. 2024. Dreammover: Leveraging the prior of diffusion models for image interpolation with large motion. In European Conference on Computer Vision. Springer, 336\u2013353."},{"key":"e_1_3_3_2_39_1","unstructured":"Ruoxi Shi Hansheng Chen Zhuoyang Zhang Minghua Liu Chao Xu Xinyue Wei Linghao Chen Chong Zeng and Hao Su. 2023. Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.15110 (2023)."},{"key":"e_1_3_3_2_40_1","unstructured":"Uriel Singer Adam Polyak Thomas Hayes Xi Yin Jie An Songyang Zhang Qiyuan Hu Harry Yang Oron Ashual Oran Gafni Devi Parikh Sonal Gupta and Yaniv Taigman. 2022. Make-A-Video: Text-to-Video Generation without Text-Video Data. arxiv:https:\/\/arXiv.org\/abs\/2209.14792\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2209.14792"},{"key":"e_1_3_3_2_41_1","unstructured":"Uriel Singer Shelly Sheynin Adam Polyak Oron Ashual Iurii Makarov Filippos Kokkinos Naman Goyal Andrea Vedaldi Devi Parikh Justin Johnson et\u00a0al. 2023. Text-to-4d dynamic scene generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.11280 (2023)."},{"key":"e_1_3_3_2_42_1","unstructured":"Florian Spiess Raphael Waltensp\u00fcl and Heiko Schuldt. 2024. The sketchfab 3d creative commons collection (s3d3c). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.17205 (2024)."},{"key":"e_1_3_3_2_43_1","unstructured":"Qi Sun Zhiyang Guo Ziyu Wan Jing\u00a0Nathan Yan Shengming Yin Wengang Zhou Jing Liao and Houqiang Li. 2024. Eg4d: Explicit generation of 4d object without score distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.18132 (2024)."},{"key":"e_1_3_3_2_44_1","unstructured":"Luming Tang Menglin Jia Qianqian Wang Cheng\u00a0Perng Phoo and Bharath Hariharan. 2023. Emergent correspondence from image diffusion. Advances in Neural Information Processing Systems 36 (2023) 1363\u20131389."},{"key":"e_1_3_3_2_45_1","unstructured":"Peng Wang and Yichun Shi. 2023. ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2312.02201\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2312.02201"},{"key":"e_1_3_3_2_46_1","volume-title":"ICLR","author":"Wang Wen","year":"2025","unstructured":"Wen Wang, Qiuyu Wang, Kecheng Zheng, Hao Ouyang, Zhekai Chen, Biao Gong, Hao Chen, Yujun Shen, and Chunhua Shen. 2025. Framer: Interactive frame interpolation. In ICLR."},{"key":"e_1_3_3_2_47_1","unstructured":"Guanjun Wu Taoran Yi Jiemin Fang Lingxi Xie Xiaopeng Zhang Wei Wei Wenyu Liu Qi Tian and Wang Xinggang. 2023b. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.08528 (2023)."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"e_1_3_3_2_50_1","unstructured":"Zijie Wu Chaohui Yu Yanqin Jiang Chenjie Cao Fan Wang and Xiang Bai. 2024. SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.03736 (2024)."},{"key":"e_1_3_3_2_51_1","unstructured":"Yiming Xie Chun-Han Yao Vikram Voleti Huaizu Jiang and Varun Jampani. 2024. Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.17470 (2024)."},{"key":"e_1_3_3_2_52_1","unstructured":"Jinbo Xing Menghan Xia Yong Zhang Haoxin Chen Xintao Wang Tien-Tsin Wong and Ying Shan. 2023. Dynamicrafter: Animating open-domain images with video diffusion priors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.12190 (2023)."},{"key":"e_1_3_3_2_53_1","first-page":"399","volume-title":"European Conference on Computer Vision","author":"Xing Jinbo","year":"2024","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2024. Dynamicrafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision. Springer, 399\u2013417."},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Ziyi Yang Xinyu Gao Wen Zhou Shaohui Jiao Yuqing Zhang and Xiaogang Jin. 2023. Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.13101 (2023).","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"e_1_3_3_2_56_1","unstructured":"Zeyu Yang Zijie Pan Chun Gu and Li Zhang. 2024b. Diffusion2: Dynamic 3d content generation via score composition of video and multi-view diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02148 (2024)."},{"key":"e_1_3_3_2_57_1","unstructured":"Yuyang Yin Dejia Xu Zhangyang Wang Yao Zhao and Yunchao Wei. 2023. 4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17225 (2023)."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"crossref","unstructured":"Yifei Zeng Yanqin Jiang Siyu Zhu Yuanxun Lu Youtian Lin Hao Zhu Weiming Hu Xun Cao and Yao Yao. 2024. Stag4d: Spatial-temporal anchored generative 4d gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14939 (2024).","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"crossref","unstructured":"Haiyu Zhang Xinyuan Chen Yaohui Wang Xihui Liu Yunhong Wang and Yu Qiao. 2024. 4diffusion: Multi-view video diffusion model for 4d generation. Advances in Neural Information Processing Systems 37 (2024) 15272\u201315295.","DOI":"10.52202\/079017-0488"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00094"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731167"},{"key":"e_1_3_3_2_62_1","unstructured":"Yi Zhou Jingwan Lu Connelly Barnes Jimei Yang Sitao Xiang and Hao li. 2020. Generative Tweening: Long-term Inbetweening of 3D Human Motions. arxiv:https:\/\/arXiv.org\/abs\/2005.08891\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2005.08891"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:34:48Z","timestamp":1765251288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763904"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":61,"alternative-id":["10.1145\/3757377.3763904","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763904","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}