Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
This addresses a domain-specific issue for 3D reconstruction and rendering, offering an incremental improvement by integrating existing priors into 3DGS optimization.
The paper tackles the problem of suboptimal geometric reconstruction in 3D Gaussian Splatting (3DGS) due to lack of explicit constraints, by incorporating a pre-trained matching prior to improve accuracy, resulting in significant advantages over state-of-the-art methods in depth rendering, mesh reconstruction, and novel view synthesis.
3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints, leading to suboptimal geometric reconstruction in regions with sparse or no observational input views. In this work, we try to mitigate the issue by incorporating a pre-trained matching prior to the 3DGS optimization process. We introduce Flow Distillation Sampling (FDS), a technique that leverages pre-trained geometric knowledge to bolster the accuracy of the Gaussian radiance field. Our method employs a strategic sampling technique to target unobserved views adjacent to the input views, utilizing the optical flow calculated from the matching model (Prior Flow) to guide the flow analytically calculated from the 3DGS geometry (Radiance Flow). Comprehensive experiments in depth rendering, mesh reconstruction, and novel view synthesis showcase the significant advantages of FDS over state-of-the-art methods. Additionally, our interpretive experiments and analysis aim to shed light on the effects of FDS on geometric accuracy and rendering quality, potentially providing readers with insights into its performance. Project page: https://nju-3dv.github.io/projects/fds