Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
By: Jiayu Yang , Weijian Su , Songqian Zhang and more
Potential Business Impact:
Makes videos of moving things look real, faster.
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.
Similar Papers
FastGS: Training 3D Gaussian Splatting in 100 Seconds
CV and Pattern Recognition
Makes 3D pictures build much faster.
RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS
CV and Pattern Recognition
Makes 3D pictures ignore moving things and changing light.
BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU
CV and Pattern Recognition
Makes 3D pictures build much faster.