{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:57:33Z","timestamp":1776445053030,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730643","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9552-4320","authenticated-orcid":false,"given":"Shuai","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8016-915X","authenticated-orcid":false,"given":"Jing","family":"Tan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0141-3939","authenticated-orcid":false,"given":"Mengchen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China and Shanghai Artificial Intelligence Laboratory, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5557-0623","authenticated-orcid":false,"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9243-6885","authenticated-orcid":false,"given":"Gordon","family":"Wetzstein","sequence":"additional","affiliation":[{"name":"Stanford University, Palo Alto, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8865-7896","authenticated-orcid":false,"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hongkong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation. arxiv:https:\/\/arXiv.org\/abs\/2302.08113\u00a0[cs.CV]"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00204"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","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. International Conference on 3D Vision (3DV) (2017).","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Zhaoxi Chen Guangcong Wang and Ziwei Liu. 2022. Text2light: Zero-shot text-driven hdr panorama generation. ACM Transactions on Graphics (TOG) 41 6 (2022) 1\u201316.","DOI":"10.1145\/3550454.3555447"},{"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. CoRR abs\/2311.13384 (2023)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Dana Cohen-Bar Elad Richardson Gal Metzer Raja Giryes and Daniel Cohen-Or. 2023. Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes. arxiv:https:\/\/arXiv.org\/abs\/2303.13450\u00a0[cs.CV]","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"e_1_3_3_2_8_1","unstructured":"Mengyang Feng Jinlin Liu Miaomiao Cui and Xuansong Xie. 2023. Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2311.13141\u00a0[cs.CV]"},{"key":"e_1_3_3_2_9_1","unstructured":"Rafail Fridman Amit Abecasis Yoni Kasten and Tali Dekel. 2023. SceneScape: Text-Driven Consistent Scene Generation. arxiv:https:\/\/arXiv.org\/abs\/2302.01133\u00a0[cs.CV]"},{"key":"e_1_3_3_2_10_1","unstructured":"Ruiqi Gao Aleksander Holynski Philipp Henzler Arthur Brussee Ricardo Martin-Brualla Pratul Srinivasan Jonathan\u00a0T Barron and Ben Poole. 2024. Cat3d: Create anything in 3d with multi-view diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.10314 (2024)."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_3_2_12_1","first-page":"6626","volume-title":"NIPS","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. In NIPS. 6626\u20136637."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Lukas H\u00f6llein Ang Cao Andrew Owens Justin Johnson and Matthias Nie\u00dfner. 2023. Text2room: Extracting textured 3d meshes from 2d text-to-image models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.11989 (2023).","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"e_1_3_3_2_14_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:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"e_1_3_3_2_16_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) 139:1\u2013139:14.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C Berg Wan-Yen Lo et\u00a0al. 2023. Segment anything. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_18_1","unstructured":"Black\u00a0Forest Labs. 2023. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_3_2_19_1","unstructured":"Yuseung Lee Kunho Kim Hyunjin Kim and Minhyuk Sung. 2023. SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions. arxiv:https:\/\/arXiv.org\/abs\/2306.05178\u00a0[cs.CV]"},{"key":"e_1_3_3_2_20_1","unstructured":"Haoran Li Haolin Shi Wenli Zhang Wenjun Wu Yong Liao Lin Wang Lik hang Lee and Pengyuan Zhou. 2024. DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling. arxiv:https:\/\/arXiv.org\/abs\/2404.03575\u00a0[cs.CV]"},{"key":"e_1_3_3_2_21_1","unstructured":"Jialu Li and Mohit Bansal. 2023. PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation. arxiv:https:\/\/arXiv.org\/abs\/2305.19195\u00a0[cs.CV]"},{"key":"e_1_3_3_2_22_1","unstructured":"Zhiheng Liu Hao Ouyang Qiuyu Wang Ka\u00a0Leong Cheng Jie Xiao Kai Zhu Nan Xue Yu Liu Yujun Shen and Yang Cao. 2024. InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.11613 (2024)."},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Anish Mittal Anush\u00a0Krishna Moorthy and Alan\u00a0Conrad Bovik. 2012a. No-reference image quality assessment in the spatial domain. IEEE Transactions on image processing 21 12 (2012) 4695\u20134708.","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Anish Mittal Rajiv Soundararajan and Alan\u00a0C Bovik. 2012b. Making a \u201ccompletely blind\u201d image quality analyzer. IEEE Signal processing letters 20 3 (2012) 209\u2013212.","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_3_2_25_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_26_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_27_1","first-page":"3762","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","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\u20133772."},{"key":"e_1_3_3_2_28_1","volume-title":"NeurIPS","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In NeurIPS."},{"key":"e_1_3_3_2_29_1","unstructured":"Gabriela Ben\u00a0Melech Stan Diana Wofk Estelle Aflalo Shao-Yen Tseng Zhipeng Cai Michael Paulitsch and Vasudev Lal. 2023. LDM3D-VR: Latent Diffusion Model for 3D VR. arxiv:https:\/\/arXiv.org\/abs\/2311.03226\u00a0[cs.CV]"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Roman Suvorov Elizaveta Logacheva Anton Mashikhin Anastasia Remizova Arsenii Ashukha Aleksei Silvestrov Naejin Kong Harshith Goka Kiwoong Park and Victor Lempitsky. 2021. Resolution-robust Large Mask Inpainting with Fourier Convolutions. arxiv:https:\/\/arXiv.org\/abs\/2109.07161\u00a0[cs.CV]","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_3_2_31_1","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:https:\/\/arXiv.org\/abs\/2412.03552 (2024)."},{"key":"e_1_3_3_2_32_1","unstructured":"Jiaxiang Tang Jiawei Ren Hang Zhou Ziwei Liu and Gang Zeng. 2023a. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16653 (2023)."},{"key":"e_1_3_3_2_33_1","unstructured":"Shitao Tang Fuyang Zhang Jiacheng Chen Peng Wang and Yasutaka Furukawa. 2023b. MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2307.01097\u00a0[cs.CV]"},{"key":"e_1_3_3_2_34_1","unstructured":"Alexander Veicht Paul-Edouard Sarlin Philipp Lindenberger and Marc Pollefeys. 2024. GeoCalib: Learning Single-image Calibration with Geometric Optimization. arxiv:https:\/\/arXiv.org\/abs\/2409.06704\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2409.06704"},{"key":"e_1_3_3_2_35_1","unstructured":"Alexander Vilesov Pradyumna Chari and Achuta Kadambi. 2023. CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting. arxiv:https:\/\/arXiv.org\/abs\/2311.17907\u00a0[cs.CV]"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Guangcong Wang Yinuo Yang Chen\u00a0Change Loy and Ziwei Liu. 2022. StyleLight: HDR Panorama Generation for Lighting Estimation and Editing. arxiv:https:\/\/arXiv.org\/abs\/2207.14811\u00a0[cs.CV]","DOI":"10.1007\/978-3-031-19784-0_28"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"crossref","unstructured":"Hai Wang Xiaoyu Xiang Yuchen Fan and Jing-Hao Xue. 2023b. Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2310.18840\u00a0[cs.CV]","DOI":"10.1109\/WACV57701.2024.00486"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"crossref","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:https:\/\/arXiv.org\/abs\/2308.14686 (2023).","DOI":"10.1145\/3581783.3612508"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618168"},{"key":"e_1_3_3_2_40_1","unstructured":"Tianhao Wu Chuanxia Zheng and Tat-Jen Cham. 2024. PanoDiffusion: 360-degree Panorama Outpainting via Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2307.03177\u00a0[cs.CV]"},{"key":"e_1_3_3_2_41_1","unstructured":"Tao Yang Peiran Ren Xuansong Xie and Lei Zhang. 2023. Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.14469 (2023)."},{"key":"e_1_3_3_2_42_1","unstructured":"Hong-Xing Yu Haoyi Duan Junhwa Hur Kyle Sargent Michael Rubinstein William\u00a0T. Freeman Forrester Cole Deqing Sun Noah Snavely Jiajun Wu and Charles Herrmann. 2023. WonderJourney: Going from Anywhere to Everywhere. CoRR abs\/2312.03884 (2023)."},{"key":"e_1_3_3_2_43_1","unstructured":"Hong-Xing Yu Haoyi Duan Charles Herrmann William\u00a0T Freeman and Jiajun Wu. 2024. 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_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"crossref","unstructured":"Jingbo Zhang Xiaoyu Li Ziyu Wan Can Wang and Jing Liao. 2024a. Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields. arxiv:https:\/\/arXiv.org\/abs\/2305.11588\u00a0[cs.CV]","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"e_1_3_3_2_46_1","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2024. Transparent Image Layer Diffusion using Latent Transparency. arxiv:https:\/\/arXiv.org\/abs\/2402.17113\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2402.17113"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"crossref","unstructured":"Qihang Zhang Chaoyang Wang Aliaksandr Siarohin Peiye Zhuang Yinghao Xu Ceyuan Yang Dahua Lin Bolei Zhou Sergey Tulyakov and Hsin-Ying Lee. 2023b. SceneWiz3D: Towards Text-guided 3D Scene Composition. arxiv:https:\/\/arXiv.org\/abs\/2312.08885\u00a0[cs.CV]","DOI":"10.1109\/CVPR52733.2024.00652"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_3_2_51_1","unstructured":"Haiyang Zhou Xinhua Cheng Wangbo Yu Yonghong Tian and Li Yuan. 2024a. 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_52_1","doi-asserted-by":"crossref","unstructured":"Shijie Zhou Zhiwen Fan Dejia Xu Haoran Chang Pradyumna Chari Tejas Bharadwaj Suya You Zhangyang Wang and Achuta Kadambi. 2024b. DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.06903 (2024).","DOI":"10.1007\/978-3-031-72658-3_19"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:04:33Z","timestamp":1774019073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":51,"alternative-id":["10.1145\/3721238.3730643","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730643","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}