{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:46:44Z","timestamp":1769636804248,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763883","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9090-6142","authenticated-orcid":false,"given":"Avinash","family":"Paliwal","sequence":"first","affiliation":[{"name":"Texas A&M University, College Station, USA and Morphic Inc, San Jose, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4133-8783","authenticated-orcid":false,"given":"Xilong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5778-9869","authenticated-orcid":false,"given":"Andrii","family":"Tsarov","sequence":"additional","affiliation":[{"name":"Leia Inc, Mountain View, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2588-9219","authenticated-orcid":false,"given":"Nima","family":"Kalantari","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Iro Armeni Sasha Sax Amir\u00a0R Zamir and Silvio Savarese. 2017. Joint 2d-3d-semantic data for indoor scene understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1702.01105 (2017)."},{"key":"e_1_3_3_2_3_1","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. Multidiffusion: Fusing diffusion paths for controlled image generation. (2023)."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00991"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00673"},{"key":"e_1_3_3_2_6_1","unstructured":"Jaeyoung Chung Suyoung Lee Hyeongjin Nam Jaerin Lee and Kyoung\u00a0Mu Lee. 2023. Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.13384 (2023)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612405"},{"key":"e_1_3_3_2_8_1","unstructured":"Paul Engstler Andrea Vedaldi Iro Laina and Christian Rupprecht. 2024. Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.19758 (2024)."},{"key":"e_1_3_3_2_9_1","unstructured":"Stanislav Frolov Brian\u00a0B Moser and Andreas Dengel. 2024. SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.15507 (2024)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"e_1_3_3_2_12_1","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685 (2021)."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01229"},{"key":"e_1_3_3_2_14_1","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_15_1","doi-asserted-by":"crossref","unstructured":"Johannes Kopf Kevin Matzen Suhib Alsisan Ocean Quigley Francis Ge Yangming Chong Josh Patterson Jan-Michael Frahm Shu Wu Matthew Yu et\u00a0al. 2020. One shot 3d photography. ACM Transactions on Graphics (TOG) 39 4 (2020) 76\u20131.","DOI":"10.1145\/3386569.3392420"},{"key":"e_1_3_3_2_16_1","unstructured":"Yuseung Lee Kunho Kim Hyunjin Kim and Minhyuk Sung. 2023. Syncdiffusion: Coherent montage via synchronized joint diffusions. Advances in Neural Information Processing Systems 36 (2023) 50648\u201350660."},{"key":"e_1_3_3_2_17_1","unstructured":"Jialu Li and Mohit Bansal. 2023. Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation. Advances in Neural Information Processing Systems 36 (2023) 21878\u201321894."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Qinbo Li and Nima\u00a0Khademi Kalantari. 2020. Synthesizing light field from a single image with variable MPI and two network fusion. ACM Trans. Graph. 39 6 (2020) 229\u20131.","DOI":"10.1145\/3414685.3417785"},{"key":"e_1_3_3_2_19_1","unstructured":"Wenrui Li Yapeng Mi Fucheng Cai Zhe Yang Wangmeng Zuo Xingtao Wang and Xiaopeng Fan. 2024. SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.13711 (2024)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"e_1_3_3_2_21_1","unstructured":"Chaojun Ni Xiaofeng Wang Zheng Zhu Weijie Wang Haoyun Li Guosheng Zhao Jie Li Wenkang Qin Guan Huang and Wenjun Mei. 2025. Wonderturbo: Generating interactive 3d world in 0.72 seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.02261 (2025)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Simon Niklaus Long Mai Jimei Yang and Feng Liu. 2019. 3d ken burns effect from a single image. ACM Transactions on Graphics (ToG) 38 6 (2019) 1\u201315.","DOI":"10.1145\/3355089.3356528"},{"key":"e_1_3_3_2_23_1","unstructured":"Hao Ouyang Kathryn Heal Stephen Lombardi and Tiancheng Sun. 2023. Text2immersion: Generative immersive scene with 3d gaussians. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.09242 (2023)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Avinash Paliwal Brandon\u00a0G Nguyen Andrii Tsarov and Nima\u00a0Khademi Kalantari. 2023. ReShader: View-Dependent Highlights for Single Image View-Synthesis. ACM Transactions on Graphics (TOG) 42 6 (2023) 1\u20139.","DOI":"10.1145\/3618393"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_2"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618155"},{"key":"e_1_3_3_2_27_1","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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00805"},{"key":"e_1_3_3_2_29_1","unstructured":"Jaidev Shriram Alex Trevithick Lingjie Liu and Ravi Ramamoorthi. 2024. Realmdreamer: Text-driven 3d scene generation with inpainting and depth diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.07199 (2024)."},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.246"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_3_2_34_1","unstructured":"Ruicheng Wang Sicheng Xu Yue Dong Yu Deng Jianfeng Xiang Zelong Lv Guangzhong Sun Xin Tong and Jiaolong Yang. 2025. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.02546 (2025)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"e_1_3_3_2_36_1","unstructured":"Haoning Wu Zicheng Zhang Weixia Zhang Chaofeng Chen Liang Liao Chunyi Li Yixuan Gao Annan Wang Erli Zhang Wenxiu Sun et\u00a0al. 2023a. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.17090 (2023)."},{"key":"e_1_3_3_2_37_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu Tianhao","year":"2023","unstructured":"Tianhao Wu, Chuanxia Zheng, and Tat-Jen Cham. 2023b. PanoDiffusion: 360-degree Panorama Outpainting via Diffusion. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_3_2_39_1","unstructured":"Lihe Yang Bingyi Kang Zilong Huang Zhen Zhao Xiaogang Xu Jiashi Feng and Hengshuang Zhao. 2024b. Depth Anything V2. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09414 (2024)."},{"key":"e_1_3_3_2_40_1","unstructured":"Weicai Ye Chenhao Ji Zheng Chen Junyao Gao Xiaoshui Huang Song-Hai Zhang Wanli Ouyang Tong He Cairong Zhao and Guofeng Zhang. 2024. DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.24203 (2024)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_3_2_42_1","unstructured":"Hong-Xing Yu Haoyi Duan Charles Herrmann William\u00a0T Freeman and Jiajun Wu. 2024a. WonderWorld: Interactive 3D Scene Generation from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09394 (2024)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Jingbo Zhang Xiaoyu Li Ziyu Wan Can Wang and Jing Liao. 2024. Text2nerf: Text-driven 3d scene generation with neural radiance fields. IEEE Transactions on Visualization and Computer Graphics (2024).","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_47_1","unstructured":"Haiyang Zhou Xinhua Cheng Wangbo Yu Yonghong Tian and Li Yuan. 2024. Holodreamer: Holistic 3d panoramic world generation from text descriptions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.15187 (2024)."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"e_1_3_3_2_50_1","first-page":"145","volume-title":"European Conference on Computer Vision","author":"Zhu Zehao","year":"2024","unstructured":"Zehao Zhu, Zhiwen Fan, Yifan Jiang, and Zhangyang Wang. 2024. Fsgs: Real-time few-shot view synthesis using gaussian splatting. In European Conference on Computer Vision. Springer, 145\u2013163."}],"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\/3757377.3763883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:26:29Z","timestamp":1765250789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":49,"alternative-id":["10.1145\/3757377.3763883","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763883","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"}}]}}