Problem
Research questions and friction points this paper is trying to address.
4D Gaussian Splatting
dynamic novel view synthesis
high-frequency motion
trajectory drift
motion modeling
FAST-GS: Frequency Aware Space-time Gaussian Splatting for Photorealistic Dynamic Novel View Synthesis
🤖 AI Summary
This work addresses the limitations of existing 4D Gaussian splatting methods in accurately modeling high-frequency motion in complex dynamic scenes and their susceptibility to trajectory drift, which compromises long-term stability. To overcome these challenges, we propose a frequency-aware spatio-temporal Gaussian splatting approach that decomposes motion into multi-frequency sinusoidal components via Fourier-based motion modeling, effectively disentangling and reconstructing both high- and low-frequency dynamics. Additionally, we introduce a frequency-weighted, motion-aware regularization strategy that enhances detail preservation and temporal consistency while maintaining real-time rendering efficiency. Experimental results demonstrate that our method significantly outperforms current state-of-the-art techniques on benchmarks such as N3V and Google Immersive, achieving superior quality in dynamic novel view synthesis.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Fourier Motion Modeling
Frequency-aware Regularization
4D Gaussian Splatting
Dynamic Novel View Synthesis
Motion Decomposition
🔎 Similar Papers
No similar papers found.
