Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation
This work addresses geometric fidelity issues in 3D reconstruction for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles geometry distortion in sparse-view 3D reconstruction using 3D Gaussian Splatting by proposing reprojection-based degree-of-freedom separation to manage positional uncertainties, resulting in reduced artifacts and more plausible reconstructions across datasets.
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.