{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:11:52Z","timestamp":1782317512454,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755133","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3615-3624","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2413-1398","authenticated-orcid":false,"given":"Yiying","family":"Yang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-1619","authenticated-orcid":false,"given":"Fukun","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China and Stepfun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4983-1353","authenticated-orcid":false,"given":"Jiayuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9755-2421","authenticated-orcid":false,"given":"Wanzhang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Santa Clara, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5570-2710","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"StepFun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Componerf: Text-guided multi-object compositional nerf with editable 3d scene layout. arXiv preprint arXiv:2303.13843","author":"Bai Haotian","year":"2023","unstructured":"Haotian Bai, Yuanhuiyi Lyu, Lutao Jiang, Sijia Li, Haonan Lu, Xiaodong Lin, and Lin Wang. 2023. Componerf: Text-guided multi-object compositional nerf with editable 3d scene layout. arXiv preprint arXiv:2303.13843 (2023)."},{"key":"e_1_3_2_1_2_1","first-page":"25102","article-title":"Gaudi: A neural architect for immersive 3d scene generation","volume":"35","author":"Bautista Miguel Angel","year":"2022","unstructured":"Miguel Angel Bautista, Pengsheng Guo, Samira Abnar, Walter Talbott, Alexander Toshev, Zhuoyuan Chen, Laurent Dinh, Shuangfei Zhai, Hanlin Goh, Daniel Ulbricht, et al., 2022. Gaudi: A neural architect for immersive 3d scene generation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25102-25116.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_22"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27886"},{"key":"e_1_3_2_1_10_1","volume-title":"V3d: Video diffusion models are effective 3d generators. arXiv preprint arXiv:2403.06738","author":"Chen Zilong","year":"2024","unstructured":"Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, and Huaping Liu. 2024b. V3d: Video diffusion models are effective 3d generators. arXiv preprint arXiv:2403.06738 (2024)."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"e_1_3_2_1_13_1","volume-title":"PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation. arXiv:2311.01773 [cs.CV]","author":"Ding Yuhan","year":"2023","unstructured":"Yuhan Ding, Fukun Yin, Jiayuan Fan, Hui Li, Xin Chen, Wen Liu, Chongshan Lu, Gang YU, and Tao Chen. 2023. PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation. arXiv:2311.01773 [cs.CV]"},{"key":"e_1_3_2_1_14_1","volume-title":"Stereoscopic displays and virtual reality systems XI","author":"Fehn Christoph","unstructured":"Christoph Fehn. 2004. Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV. In Stereoscopic displays and virtual reality systems XI, Vol. 5291. SPIE, 93-104."},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Fridman Rafail","year":"2024","unstructured":"Rafail Fridman, Amit Abecasis, Yoni Kasten, and Tali Dekel. 2024. Scenescape: Text-driven consistent scene generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_16_1","first-page":"31841","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","volume":"35","author":"Gao Jun","year":"2022","unstructured":"Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. Get3d: A generative model of high quality 3d textured shapes learned from images. Advances In Neural Information Processing Systems, Vol. 35 (2022), 31841-31854.","journal-title":"Advances In Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Chitwan Saharia, William Chan, David J Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded diffusion models for high fidelity image generation. Journal of Machine Learning Research, Vol. 23, 47 (2022), 1-33.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3265201"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01230"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00188"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","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, 12888-12900."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25224"},{"key":"e_1_3_2_1_28_1","volume-title":"Unbounded-GS: Extending 3D Gaussian splatting with hybrid representation for unbounded large-scale scene reconstruction","author":"Li Wanzhang","year":"2024","unstructured":"Wanzhang Li, Fukun Yin, Wen Liu, Yiying Yang, Xin Chen, Biao Jiang, Gang Yu, and Jiayuan Fan. 2024. Unbounded-GS: Extending 3D Gaussian splatting with hybrid representation for unbounded large-scale scene reconstruction. IEEE Robotics and Automation Letters (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453","author":"Liu Yuan","year":"2023","unstructured":"Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2023. Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction. arXiv preprint arXiv:2301.06782","author":"Lu Chongshan","year":"2023","unstructured":"Chongshan Lu, Fukun Yin, Xin Chen, Tao Chen, Gang Yu, and Jiayuan Fan. 2023. A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction. arXiv preprint arXiv:2301.06782 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10209-10218","author":"Luo Zhengxiong","year":"2023","unstructured":"Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jingren Zhou, and Tieniu Tan. 2023. Videofusion: Decomposed diffusion models for high-quality video generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10209-10218."},{"key":"e_1_3_2_1_33_1","volume-title":"IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation. arXiv preprint arXiv:2402.08682","author":"Melas-Kyriazi Luke","year":"2024","unstructured":"Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, and Filippos Kokkinos. 2024. IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation. arXiv preprint arXiv:2402.08682 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00956"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_37_1","volume-title":"Making a ''completely blind'' image quality analyzer","author":"Mittal Anish","year":"2012","unstructured":"Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. 2012b. Making a ''completely blind'' image quality analyzer. IEEE Signal processing letters, Vol. 20, 3 (2012), 209-212."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7588-7597","author":"Nguyen-Phuoc Thu","year":"2019","unstructured":"Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, and Yong-Liang Yang. 2019. Hologan: Unsupervised learning of 3d representations from natural images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7588-7597."},{"key":"e_1_3_2_1_39_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"e_1_3_2_1_41_1","volume-title":"Compositional 3d scene generation using locally conditioned diffusion. arXiv preprint arXiv:2303.12218","author":"Po Ryan","year":"2023","unstructured":"Ryan Po and Gordon Wetzstein. 2023. Compositional 3d scene generation using locally conditioned diffusion. arXiv preprint arXiv:2303.12218 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01384"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_46_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211-252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00391"},{"key":"e_1_3_2_1_49_1","volume-title":"Dmitry Lagun, Li Fei-Fei, Deqing Sun, et al.","author":"Sargent Kyle","year":"2023","unstructured":"Kyle Sargent, Zizhang Li, Tanmay Shah, Charles Herrmann, Hong-Xing Yu, Yunzhi Zhang, Eric Ryan Chan, Dmitry Lagun, Li Fei-Fei, Deqing Sun, et al., 2023b. Zeronvs: Zero-shot 360-degree view synthesis from a single real image. arXiv preprint arXiv:2310.17994 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Sch\u00f6nberger Johannes Lutz","year":"2016","unstructured":"Johannes Lutz Sch\u00f6nberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_51_1","volume-title":"Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV).","author":"Sch\u00f6nberger Johannes Lutz","year":"2016","unstructured":"Johannes Lutz Sch\u00f6nberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_52_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","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, et al., 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278-25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"e_1_3_2_1_54_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_55_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"key":"e_1_3_2_1_56_1","volume-title":"Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion. arXiv preprint arXiv:2403.12008","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. arXiv preprint arXiv:2403.12008 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Wang Guangcong","year":"2023","unstructured":"Guangcong Wang, Peng Wang, Zhaoxi Chen, Wenping Wang, Chen Change Loy, and Ziwei Liu. 2023b. PERF: Panoramic Neural Radiance Field from a Single Panorama. arXiv preprint arXiv:2310.16831 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"e_1_3_2_1_59_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Zhengyi","year":"2024","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2024. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_60_1","volume-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Advances in neural information processing systems","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. 2016. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_3_2_1_63_1","volume-title":"VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations. arXiv preprint arXiv:2310.14487","author":"Yang Yiying","year":"2023","unstructured":"Yiying Yang, Wen Liu, Fukun Yin, Xin Chen, Gang Yu, Jiayuan Fan, and Tao Chen. 2023a. VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations. arXiv preprint arXiv:2310.14487 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28481"},{"key":"e_1_3_2_1_65_1","volume-title":"Shapegpt: 3d shape generation with a unified multi-modal language model","author":"Yin Fukun","year":"2025","unstructured":"Fukun Yin, Xin Chen, Chi Zhang, Biao Jiang, Zibo Zhao, Wen Liu, Gang Yu, and Tao Chen. 2025. Shapegpt: 3d shape generation with a unified multi-modal language model. IEEE Transactions on Multimedia (2025)."},{"key":"e_1_3_2_1_66_1","volume-title":"Dcnet: Large-scale point cloud semantic segmentation with discriminative and efficient feature aggregation","author":"Yin Fukun","year":"2023","unstructured":"Fukun Yin, Zilong Huang, Tao Chen, Guozhong Luo, Gang Yu, and Bin Fu. 2023. Dcnet: Large-scale point cloud semantic segmentation with discriminative and efficient feature aggregation. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_67_1","unstructured":"Fukun Yin Wen Liu Zilong Huang Pei Cheng Tao Chen and Gang YU. 2022. Coordinates Are NOT Lonely-Codebook Prior Helps Implicit Neural 3D Representations. arXiv preprint arXiv:2210.11170 (2022)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00829"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_71_1","unstructured":"Hong-Xing Yu Haoyi Duan Junhwa Hur Kyle Sargent Michael Rubinstein William T Freeman Forrester Cole Deqing Sun Noah Snavely Jiajun Wu et al. 2023. WonderJourney: Going from Anywhere to Everywhere. arXiv preprint arXiv:2312.03884 (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation. arXiv preprint arXiv:2403.09439","author":"Zhang Frank","year":"2024","unstructured":"Frank Zhang, Yibo Zhang, Quan Zheng, Rui Ma, Wei Hua, Hujun Bao, Weiwei Xu, and Changqing Zou. 2024b. 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation. arXiv preprint arXiv:2403.09439 (2024)."},{"key":"e_1_3_2_1_73_1","volume-title":"Text2nerf: Text-driven 3d scene generation with neural radiance fields","author":"Zhang Jingbo","year":"2024","unstructured":"Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, and Jing Liao. 2024a. Text2nerf: Text-driven 3d scene generation with neural radiance fields. IEEE Transactions on Visualization and Computer Graphics (2024)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01691-w"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3330518"}],"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\/3746027.3755133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:01:03Z","timestamp":1765310463000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":75,"alternative-id":["10.1145\/3746027.3755133","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755133","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"}}]}}