DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstruction
It addresses the problem of reconstructing intricate, ever-changing environments for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles dynamic scene reconstruction by extending Gaussian Splatting with dynamic-static separation and hierarchical motion modeling, achieving state-of-the-art accuracy and realism in experiments.
Reconstructing intricate, ever-changing environments remains a central ambition in computer vision, yet existing solutions often crumble before the complexity of real-world dynamics. We present DynaSplat, an approach that extends Gaussian Splatting to dynamic scenes by integrating dynamic-static separation and hierarchical motion modeling. First, we classify scene elements as static or dynamic through a novel fusion of deformation offset statistics and 2D motion flow consistency, refining our spatial representation to focus precisely where motion matters. We then introduce a hierarchical motion modeling strategy that captures both coarse global transformations and fine-grained local movements, enabling accurate handling of intricate, non-rigid motions. Finally, we integrate physically-based opacity estimation to ensure visually coherent reconstructions, even under challenging occlusions and perspective shifts. Extensive experiments on challenging datasets reveal that DynaSplat not only surpasses state-of-the-art alternatives in accuracy and realism but also provides a more intuitive, compact, and efficient route to dynamic scene reconstruction.