FAST-GS: Frequency Aware Space-time Gaussian Splatting for Photorealistic Dynamic Novel View Synthesis
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors improved a method called 4D Gaussian Splatting, which helps create 3D videos that can be viewed from different angles in real time. They noticed that the old method used a simple motion model that struggled with fast or complicated movements and could get unstable over time. To fix this, they introduced a new way to break down motion into waves of different speeds, capturing both slow and fast movements better, while still being fast enough to render in real time. They also added a new way to make sure the motion looks smooth and stable. Tests on real datasets showed their method works better with complex motions.
4D Gaussian Splattingdynamic 3D reconstructionnovel view synthesismotion modelingFourier decompositionfrequency componentsreal-time renderingtrajectory driftregularizationmotion coherence
Authors
Zhengyang Zhang, Ziyu Lu, PengCheng Li, Hongbo Duan, Yi Liu, Pengting Luo, Peiyu Zhuang, Xinghui Li, Shaohua Ma
Abstract
4D Gaussian Splatting (4DGS) excels in dynamic 3D reconstruction and real-time novel view synthesis via efficient 4D Gaussian representations and parallelizable rendering. However, existing 4DGS approaches rely on a single polynomial to model motion, which limits performance in complex dynamic scenes where high-frequency motion components are prevalent, and fails to ensure long-term stability due to cumulative trajectory drift. To address these issues, we propose a Fourier Motion Modeling module: this paradigm decomposes motion into frequency-based sinusoidal components, capturing both low-frequency global trajectories and high-frequency local details to model complex motion patterns accurately. It retains the real-time rendering capability of 4DGS while improving complex motion fitting and long-term coherence. Additionally, we integrate a motion-aware regularization strategy into the loss function: it uses frequency-dependent weights to suppress high-frequency jitter while preserving low-frequency motion coherence. Extensive experiments on N3V and Google Immersive datasets from multiple scenarios demonstrate the effectiveness of our method.