The paper "VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction" addresses the challenge of extracting high-quality surfaces from point-based representations using 3D Gaussian Splatting. The authors propose a novel view-consistent Depth-Normal (D-Normal) regularizer that directly couples normal with other geometric parameters, enabling full updates of geometric parameters through normal regularization. They introduce a confidence term to mitigate inconsistencies in normal predictions across multiple views and a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. The method outperforms existing Gaussian-based baselines in terms of reconstruction quality and rendering speed, achieving competitive appearance quality at faster training speeds and 100+ FPS rendering. The code will be made open-source upon paper acceptance.The paper "VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction" addresses the challenge of extracting high-quality surfaces from point-based representations using 3D Gaussian Splatting. The authors propose a novel view-consistent Depth-Normal (D-Normal) regularizer that directly couples normal with other geometric parameters, enabling full updates of geometric parameters through normal regularization. They introduce a confidence term to mitigate inconsistencies in normal predictions across multiple views and a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. The method outperforms existing Gaussian-based baselines in terms of reconstruction quality and rendering speed, achieving competitive appearance quality at faster training speeds and 100+ FPS rendering. The code will be made open-source upon paper acceptance.