Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
This work addresses the challenge of efficient real-time rendering for immersive applications, representing an incremental improvement over existing 3D Gaussian Splatting methods.
The paper tackles the problem of extending 3D Gaussian Splatting to dynamic scenes by addressing limitations in data volume and training time, resulting in a framework that achieves superior visual quality and significantly reduces training time compared to state-of-the-art methods.
3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, a key requirement for immersive applications. However, the extension of 3DGS to dynamic scenes remains limitations on the substantial data volume of dense Gaussians and the prolonged training time required for each frame. This paper presents \M, a scalable Gaussian Splatting framework designed for efficient training in streaming tasks. Specifically, Gaussian spheres are hierarchically organized by scale within an anchor-based structure. Coarser-level Gaussians represent the low-resolution structure of the scene, while finer-level Gaussians, responsible for detailed high-fidelity rendering, are selectively activated by the coarser-level Gaussians. To further reduce computational overhead, we introduce a hybrid deformation and spawning strategy that models motion of inter-frame through Gaussian deformation and triggers Gaussian spawning to characterize wide-range motion. Additionally, a bidirectional adaptive masking mechanism enhances training efficiency by removing static regions and prioritizing informative viewpoints. Extensive experiments demonstrate that \M~ achieves superior visual quality while significantly reducing training time compared to state-of-the-art methods.