FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction
Yifan Wang, Peishan Yang, Zhen Xu, Jiaming Sun, Zhanhua Zhang, Yong Chen, Hujun Bao, Sida Peng, Xiaowei Zhou
2025年份
7顶会引用
摘要
25.98 dB 26.75 dB Figure 1 . Photorealistic and real-time rendering of dynamic 3D scenes. Our method achieves the best performance on challenging dynamic scenes with fast and complex motion. Compared with current state-of-the-art methods 4DGS [48] and STGS [21], our PSNR is improved by 2.4dB and 1.4dB on the SelfCap dataset. For dynamic regions, our PSNR is improved by 4.1dB and 2.6dB. What's more, our method supports real-time rendering at 1080p resolution with a speed of 450 FPS using a single RTX 4090 GPU.
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 Paper7
- PerpetualWonder: Long-horizon Action-conditioned 4D Scene GenerationJiahao Zhan, Zizhang Li, Hong-Xing Yu, Jiajun WuCVPR 2026 · 被引用 9 次
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video ReconstructionJiacong Chen, Qingyu Mao, Youneng Bao, Xiandong Meng 等NeurIPS 2025 · 被引用 7 次
- 4D Human-Scene Reconstruction from Low-Overlap CapturesMinhyuk Hwang, Sangmin Kim, Seunguk Do, Daneul Kim 等SIGGRAPH 2026
- Taylor-Gaussians-Flow: Towards Non-uniform Motion for Novel View Synthesis from Monocular VideoYan Zaoming, Qizhou Chen, Yaomin Huang, Pengcheng Lei 等ICML 2026
- Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting under UncertaintyDoga Yilmaz, Jialin Zhu, Deshan Gong, He WangSIGGRAPH 2026
它引用的顶会 Paper20
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingZeyu Yang, Hongye Yang, Zijie Pan, Li ZhangICLR 2024 · 被引用 529 次
- Neural 3D Video Synthesis from Multi-view VideoTianye Li, Mira Slavcheva, Michael Zollhöfer, Simon Green 等CVPR 2022 · 被引用 324 次
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionZiyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao 等CVPR 2024 · 被引用 302 次
- NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance FieldsLiangchen Song, Anpei Chen, Zhong Li, Zhang Chen 等IEEE VR 2023 · 被引用 246 次
相关 Paper
- 4K4D: Real-Time 4D View Synthesis at 4K ResolutionZhen Xu, Sida Peng, Haotong Lin, Guangzhao He 等CVPR 2024
- ST-4DGS: Spatial-Temporally Consistent 4D Gaussian Splatting for Efficient Dynamic Scene RenderingDeqi Li, Shi-Sheng Huang, Zhiyuan Lu, Xinran Duan 等SIGGRAPH 2024 · 被引用 33 次
- DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene RenderingJie Chen, Zhangchi Hu, Peixi Wu, Huyue Zhu 等ICCV 2025 · 被引用 2 次
- EnvGS: Modeling View-Dependent Appearance with Environment GaussianTao Xie, Xi Chen, Zhen Xu, Yiman Xie 等CVPR 2025
- Layered 4D-Rotor Gaussian Splatting: A Compressed Representation for Long Dynamic ScenesHanjie Xu, Yuanxing Duan, Qiyu Dai, Ge Li 等CVPR 2026
