AI Insight
This paper introduces FAST-GS, a new method for creating photorealistic videos from novel viewpoints of dynamic 3D scenes. The approach improves upon existing 4D Gaussian Splatting techniques by using Fourier-based decomposition to model motion as a combination of frequency components, rather than relying on a single polynomial function. This frequency-aware approach better captures both smooth global motion and rapid local movements while maintaining real-time rendering capabilities and reducing long-term trajectory drift in complex dynamic scenes.
Why it matters
The method could enhance applications requiring real-time 3D video reconstruction and novel view synthesis, such as virtual reality, augmented reality, autonomous vehicle systems, and video production. By improving the accuracy and stability of dynamic scene reconstruction, it may enable more realistic and reliable representations of moving objects and environments in computer vision systems.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
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.