{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:26Z","timestamp":1784268386154,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024XKRC082"],"award-info":[{"award-number":["2024XKRC082"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.92470203"],"award-info":[{"award-number":["No.92470203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["No. L242022"],"award-info":[{"award-number":["No. L242022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754704","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"9267-9276","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["TiP4GEN: Text to Immersive Panorama 4D Scene Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2626-9072","authenticated-orcid":false,"given":"Ke","family":"Xing","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9892-752X","authenticated-orcid":false,"given":"Hanwen","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8474-3095","authenticated-orcid":false,"given":"Dejia","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7443-6194","authenticated-orcid":false,"given":"Yuyang","family":"Yin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3647-5473","authenticated-orcid":false,"given":"Konstantinos N.","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"e_1_3_2_1_2_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_4_1","volume-title":"Matterport3d: Learning from rgb-d data in indoor environments. arXiv preprint arXiv:1709.06158","author":"Chang Angel","year":"2017","unstructured":"Angel Chang, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Niessner, Manolis Savva, Shuran Song, Andy Zeng, and Yinda Zhang. 2017. Matterport3d: Learning from rgb-d data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"Follow-your-canvas: Higher-resolution video outpainting with extensive content generation. arXiv preprint arXiv:2409.01055","author":"Chen Qihua","year":"2024","unstructured":"Qihua Chen, Yue Ma, Hongfa Wang, Junkun Yuan, Wenzhe Zhao, Qi Tian, Hongmei Wang, Shaobo Min, Qifeng Chen, and Wei Liu. 2024. Follow-your-canvas: Higher-resolution video outpainting with extensive content generation. arXiv preprint arXiv:2409.01055 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:2311.13384","author":"Chung Jaeyoung","year":"2023","unstructured":"Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, and Kyoung Mu Lee. 2023. Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:2311.13384 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00059"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612405"},{"key":"e_1_3_2_1_9_1","volume-title":"Ctrl-Room: controllable text-to-3D room meshes generation with layout constraints. arXiv preprint arXiv:2310.03602","author":"Fang Chuan","year":"2023","unstructured":"Chuan Fang, Yuan Dong, Kunming Luo, Xiaotao Hu, Rakesh Shrestha, and Ping Tan. 2023. Ctrl-Room: controllable text-to-3D room meshes generation with layout constraints. arXiv preprint arXiv:2310.03602 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221","author":"He Yingqing","year":"2022","unstructured":"Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_15_1","volume-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868","author":"Hong Wenyi","year":"2022","unstructured":"Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, and Jie Tang. 2022. Cogvideo: Large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Wenyi Hong Weihan Wang Qingsong Lv Jiazheng Xu Wenmeng Yu Junhui Ji Yan Wang Zihan Wang Yuxiao Dong Ming Ding and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. arXiv:2312.08914 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_1_17_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_19_1","volume-title":"Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems, Vol. 35 (2022), 26565-26577."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_21_1","volume-title":"Vividdream: Generating 3d scene with ambient dynamics. arXiv preprint arXiv:2405.20334","author":"Lee Yao-Chih","year":"2024","unstructured":"Yao-Chih Lee, Yi-Ting Chen, Andrew Wang, Ting-Hsuan Liao, Brandon Y Feng, and Jia-Bin Huang. 2024. Vividdream: Generating 3d scene with ambient dynamics. arXiv preprint arXiv:2405.20334 (2024)."},{"key":"e_1_3_2_1_22_1","first-page":"21878","article-title":"Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation","volume":"36","author":"Li Jialu","year":"2023","unstructured":"Jialu Li and Mohit Bansal. 2023. Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 21878-21894.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","unstructured":"Renjie Li Panwang Pan Bangbang Yang Dejia Xu Shijie Zhou Xuanyang Zhang Zeming Li Achuta Kadambi Zhangyang Wang Zhengzhong Tu et al. 2024. 4k4dgen: Panoramic 4d generation at 4k resolution. arXiv preprint arXiv:2406.13527 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00446"},{"key":"e_1_3_2_1_25_1","volume-title":"Wonderland: Navigating 3D Scenes from a Single Image. arXiv preprint arXiv:2412.12091","author":"Liang Hanwen","year":"2024","unstructured":"Hanwen Liang, Junli Cao, Vidit Goel, Guocheng Qian, Sergei Korolev, Demetri Terzopoulos, Konstantinos N Plataniotis, Sergey Tulyakov, and Jian Ren. 2024a. Wonderland: Navigating 3D Scenes from a Single Image. arXiv preprint arXiv:2412.12091 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models. arXiv preprint arXiv:2405.16645","author":"Liang Hanwen","year":"2024","unstructured":"Hanwen Liang, Yuyang Yin, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N Plataniotis, Yao Zhao, and Yunchao Wei. 2024b. Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models. arXiv preprint arXiv:2405.16645 (2024)."},{"key":"e_1_3_2_1_27_1","first-page":"22226","article-title":"One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu Minghua","year":"2023","unstructured":"Minghua Liu, Chao Xu, Haian Jin, Linghao Chen, Mukund Varma T, Zexiang Xu, and Hao Su. 2023. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. Advances in Neural Information Processing Systems, Vol. 36 (2023), 22226-22246.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","volume-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177","author":"Liu Yixin","year":"2024","unstructured":"Yixin Liu, Kai Zhang, Yuan Li, Zhiling Yan, Chujie Gao, Ruoxi Chen, Zhengqing Yuan, Yue Huang, Hanchi Sun, Jianfeng Gao, et al., 2024. Sora: A review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing 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 Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 5775-5787. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/260a14acce2a89dad36adc8eefe7c59e-Paper-Conference.pdf"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"e_1_3_2_1_31_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_32_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01952"},{"key":"e_1_3_2_1_34_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3762-3772","author":"Rey-Area Manuel","year":"2022","unstructured":"Manuel Rey-Area, Mingze Yuan, and Christian Richardt. 2022. 360monodepth: High-resolution 360deg monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3762-3772."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_38_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_39_1","volume-title":"Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512","author":"Shi Yichun","year":"2023","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, and Xiao Yang. 2023. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00413"},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. pmlr, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. pmlr, 2256-2265."},{"key":"e_1_3_2_1_42_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_43_1","volume-title":"Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor. arXiv preprint arXiv:2412.03552","author":"Tan Jing","year":"2024","unstructured":"Jing Tan, Shuai Yang, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, and Dahua Lin. 2024. Imagine360: Immersive 360 Video Generation from Perspective Anchor. arXiv preprint arXiv:2412.03552 (2024)."},{"key":"e_1_3_2_1_45_1","unstructured":"Shitao Tang Fuyang Zhang Jiacheng Chen Peng Wang and Yasutaka Furukawa. 2023. MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion. arXiv:2307.01097 [cs.CV] https:\/\/arxiv.org\/abs\/2307.01097"},{"key":"e_1_3_2_1_46_1","volume-title":"Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly.","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)."},{"key":"e_1_3_2_1_47_1","volume-title":"European Conference on Computer Vision. Springer, 439-457","author":"Voleti Vikram","year":"2024","unstructured":"Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, and Varun Jampani. 2024. Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion. In European Conference on Computer Vision. Springer, 439-457."},{"key":"e_1_3_2_1_48_1","volume-title":"Willi Menapace, Aliaksandr Siarohin, Michael Vasilkovsky, Ivan Skorokhodov, Sergey Tulyakov, Peter Wonka, and Hsin-Ying Lee.","author":"Wang Chaoyang","year":"2024","unstructured":"Chaoyang Wang, Peiye Zhuang, Tuan Duc Ngo, Willi Menapace, Aliaksandr Siarohin, Michael Vasilkovsky, Ivan Skorokhodov, Sergey Tulyakov, Peter Wonka, and Hsin-Ying Lee. 2024c. 4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion. arXiv preprint arXiv:2412.04462 (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"e_1_3_2_1_50_1","volume-title":"360-degree panorama generation from few unregistered nfov images. arXiv preprint arXiv:2308.14686","author":"Wang Jionghao","year":"2023","unstructured":"Jionghao Wang, Ziyu Chen, Jun Ling, Rong Xie, and Li Song. 2023a. 360-degree panorama generation from few unregistered nfov images. arXiv preprint arXiv:2308.14686 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00660"},{"key":"e_1_3_2_1_52_1","unstructured":"Weihan Wang Qingsong Lv Wenmeng Yu Wenyi Hong Ji Qi Yan Wang Junhui Ji Zhuoyi Yang Lei Zhao Xixuan Song Jiazheng Xu Bin Xu Juanzi Li Yuxiao Dong Ming Ding and Jie Tang. 2023b. CogVLM: Visual Expert for Pretrained Language Models. arXiv:2311.03079 [cs.CV]"},{"key":"e_1_3_2_1_53_1","volume-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090","author":"Wu Haoning","year":"2023","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2023a. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Cat4d: Create anything in 4d with multi-view video diffusion models. arXiv preprint arXiv:2411.18613","author":"Wu Rundi","year":"2024","unstructured":"Rundi Wu, Ruiqi Gao, Ben Poole, Alex Trevithick, Changxi Zheng, Jonathan T Barron, and Aleksander Holynski. 2024. Cat4d: Create anything in 4d with multi-view video diffusion models. arXiv preprint arXiv:2411.18613 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Ipo-ldm: Depth-aided 360-degree indoor rgb panorama outpainting via latent diffusion model. arXiv preprint arXiv:2307.03177","author":"Wu Tianhao","year":"2023","unstructured":"Tianhao Wu, Chuanxia Zheng, and Tat-Jen Cham. 2023b. Ipo-ldm: Depth-aided 360-degree indoor rgb panorama outpainting via latent diffusion model. arXiv preprint arXiv:2307.03177, Vol. 3 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Comp4d: Llm-guided compositional 4d scene generation. arXiv preprint arXiv:2403.16993","author":"Xu Dejia","year":"2024","unstructured":"Dejia Xu, Hanwen Liang, Neel P Bhatt, Hezhen Hu, Hanxue Liang, Konstantinos N Plataniotis, and Zhangyang Wang. 2024. Comp4d: Llm-guided compositional 4d scene generation. arXiv preprint arXiv:2403.16993 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"Layerpano3d: Layered 3d panorama for hyper-immersive scene generation. arXiv preprint arXiv:2408.13252","author":"Yang Shuai","year":"2024","unstructured":"Shuai Yang, Jing Tan, Mengchen Zhang, Tong Wu, Yixuan Li, Gordon Wetzstein, Ziwei Liu, and Dahua Lin. 2024. Layerpano3d: Layered 3d panorama for hyper-immersive scene generation. arXiv preprint arXiv:2408.13252 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency. arXiv preprint arXiv:2312.17225","author":"Yin Yuyang","year":"2023","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:2312.17225 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Wonderworld: Interactive 3d scene generation from a single image. arXiv preprint arXiv:2406.09394","author":"Yu Hong-Xing","year":"2024","unstructured":"Hong-Xing Yu, Haoyi Duan, Charles Herrmann, William T Freeman, and Jiajun Wu. 2024. Wonderworld: Interactive 3d scene generation from a single image. arXiv preprint arXiv:2406.09394 (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"e_1_3_2_1_61_1","volume-title":"Monst3r: A simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:2410.03825","author":"Zhang Junyi","year":"2024","unstructured":"Junyi Zhang, Charles Herrmann, Junhwa Hur, Varun Jampani, Trevor Darrell, Forrester Cole, Deqing Sun, and Ming-Hsuan Yang. 2024a. Monst3r: A simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:2410.03825 (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"European Conference on Computer Vision. Springer, 324-342","author":"Zhou Shijie","year":"2024","unstructured":"Shijie Zhou, Zhiwen Fan, Dejia Xu, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, and Achuta Kadambi. 2024. Dreamscene360: Unconstrained text-to-3d scene generation with panoramic gaussian splatting. In European Conference on Computer Vision. Springer, 324-342."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20278"},{"key":"e_1_3_2_1_64_1","volume-title":"Videomv: Consistent multi-view generation based on large video generative model.","author":"Zuo Qi","year":"2024","unstructured":"Qi Zuo, Xiaodong Gu, Lingteng Qiu, Yuan Dong, Weihao Yuan, Rui Peng, Siyu Zhu, Liefeng Bo, Zilong Dong, Qixing Huang, et al., 2024. Videomv: Consistent multi-view generation based on large video generative model. (2024)."}],"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\/3746027.3754704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:07:45Z","timestamp":1765343265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3754704","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754704","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"}}]}}