SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
This work addresses efficiency limitations in dynamic scene reconstruction for applications like computer graphics and VR, representing an incremental improvement over existing Gaussian frameworks.
The paper tackled the trade-off between storage costs and motion modeling in dynamic scene reconstruction by proposing SD-GS, which reduces model size by 60% and improves FPS by 100% compared to state-of-the-art methods while maintaining visual quality.
Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions significantly limits the practical application of these methods. To tackle these problems, we propose SD-GS, a compact and efficient dynamic Gaussian splatting framework for complex dynamic scene reconstruction, featuring two key contributions. First, we introduce a deformable anchor grid, a hierarchical and memory-efficient scene representation where each anchor point derives multiple 3D Gaussians in its local spatiotemporal region and serves as the geometric backbone of the 3D scene. Second, to enhance modeling capability for complex motions, we present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions while reducing redundancy in static areas, achieving superior visual quality with fewer anchors. Experimental results demonstrate that, compared to state-of-the-art methods, SD-GS achieves an average of 60\% reduction in model size and an average of 100\% improvement in FPS, significantly enhancing computational efficiency while maintaining or even surpassing visual quality.