Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation

TL;DR

This paper introduces a reprojection-based method to separate and constrain positional degrees of freedom in 3D Gaussian Splatting, significantly reducing geometric distortions in sparse-view 3D reconstruction.

Contribution

It proposes a novel DoF separation technique with tailored constraints, improving structural fidelity in 3D Gaussian Splatting for sparse-view reconstruction.

Findings

Reduces geometric artifacts in 3D reconstructions

Enhances structural fidelity and visual plausibility

Effective across various datasets

Abstract

Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction. However, directly applying 3D Gaussian Splatting (3DGS) as a refinement step following these models presents challenges. We hypothesize that the excessive positional degrees of freedom (DoFs) in Gaussians induce geometry distortion, fitting color patterns at the cost of structural fidelity. To address this, we propose reprojection-based DoF separation, a method distinguishing positional DoFs in terms of uncertainty: image-plane-parallel DoFs and ray-aligned DoF. To independently manage each DoF, we introduce a reprojection process along with tailored constraints for each DoF. Through experiments across various datasets, we confirm that separating the positional DoFs of Gaussians and applying targeted constraints effectively suppresses geometric artifacts, producing reconstruction results that are both visually and geometrically plausible.