Imagine360: Immersive 360 Video Generation from Perspective Anchor
Jing Tan, Shuai Yang, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, Dahua Lin
摘要
videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more user-friendly and personalized content creation in video format, we seek to lift standard perspective videos into equirectangular videos. To this end, we introduce Imagine360, the first perspective-to- video generation framework that creates high-quality videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited video data with several key designs. 1) Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for video generation, with motion module and spatial LoRA layers fine-tuned on extended web videos. 2) Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. 3) To handle diverse perspective video inputs, we propose elevation-aware designs that adapt to varying video masking due to changing elevations across frames. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence among state-of-the-art video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive video creation.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper10
- LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text EncodersBoyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang 等NeurIPS 2025 · 被引用 17 次
- Conditional Panoramic Image Generation via Masked Autoregressive ModelingChaoyang Wang, Xiangtai Li, Lu Qi, Xiaofan Lin 等NeurIPS 2025 · 被引用 11 次
- CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective VideoLingen Li, Guangzhi Wang, Xiaoyu Li, Zhaoyang Zhang 等CVPR 2026 · 被引用 10 次
- HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationHaiyang Zhou, Wangbo Yu, Jiawen Guan, Xinhua Cheng 等ACM MM 2025 · 被引用 4 次
- Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video DiffusionTing-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee 等CVPR 2026 · 被引用 2 次
它引用的顶会 Paper21
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningYuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang 等ICLR 2024 · 被引用 1,493 次
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware DiffusionShitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang 等NeurIPS 2023 · 被引用 249 次
- TTT3R: 3D Reconstruction as Test-Time TrainingXingyu Chen, Yue Chen, Yuliang Xiu, Andreas Geiger 等ICLR 2026 · 被引用 139 次
相关 Paper
- Beyond the Frame: Generating 360° Panoramic Videos from Perspective VideosRundong Luo, Matthew Wallingford, Ali Farhadi, Noah Snavely 等ICCV 2025 · 被引用 2 次
- 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion ModelQian Wang, Weiqi Li, Chong Mou, Xinhua Cheng 等CVPR 2024 · 被引用 23 次
- Image as a World: Generating Interactive World from Single Image via Panoramic Video GenerationDongnan Gui, Xun Guo, Wengang Zhou, Yan LuNeurIPS 2025 · 被引用 5 次
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion ModelsZixun Fang, Kai Zhu, Zhiheng Liu, Yu Liu 等NeurIPS 2025 · 被引用 2 次
- PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video DiffusionYuyang Yin, Hao-Xiang Guo, Fangfu Liu, Mengyu Wang 等ICML 2026 · 被引用 3 次
