Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting
This work addresses the challenge of maintaining coherent motion and local geometric structure in dynamic 3D reconstruction, which is crucial for applications in computer vision and graphics, though it appears to be an incremental improvement over existing Gaussian Splatting methods.
The paper tackles the problem of modeling realistic motion in dynamic 3D scene reconstruction using 3D Gaussian Splatting, particularly for monocular video datasets, by proposing a view-space ray grouping strategy that clusters Gaussians intersected by the same ray and applies constraints to maintain consistent spatial distribution. The result is a method that significantly outperforms existing approaches, achieving superior temporal consistency and reconstruction quality without relying on external priors like optical flow.
The reconstruction of dynamic 3D scenes using 3D Gaussian Splatting has shown significant promise. A key challenge, however, remains in modeling realistic motion, as most methods fail to align the motion of Gaussians with real-world physical dynamics. This misalignment is particularly problematic for monocular video datasets, where failing to maintain coherent motion undermines local geometric structure, ultimately leading to degraded reconstruction quality. Consequently, many state-of-the-art approaches rely heavily on external priors, such as optical flow or 2D tracks, to enforce temporal coherence. In this work, we propose a novel method to explicitly preserve the local geometric structure of Gaussians across time in 4D scenes. Our core idea is to introduce a view-space ray grouping strategy that clusters Gaussians intersected by the same ray, considering only those whose $α$-blending weights exceed a threshold. We then apply constraints to these groups to maintain a consistent spatial distribution, effectively preserving their local geometry. This approach enforces a more physically plausible motion model by ensuring that local geometry remains stable over time, eliminating the reliance on external guidance. We demonstrate the efficacy of our method by integrating it into two distinct baseline models. Extensive experiments on challenging monocular datasets show that our approach significantly outperforms existing methods, achieving superior temporal consistency and reconstruction quality.