GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction
This work improves surface reconstruction for 3D modeling applications, though it is incremental as it builds on prior Gaussian-based methods.
The paper tackles the challenge of accurate surface reconstruction from 3D Gaussian Splatting by addressing unreliable multi-view constraints and scale ambiguity in monocular depth priors, resulting in consistent improvements in geometric accuracy on DTU and TNT datasets.
3D Gaussian Splatting enables efficient optimization and high-quality rendering, yet accurate surface reconstruction remains challenging. Prior methods improve surface reconstruction by refining Gaussian depth estimates, either via multi-view geometric consistency or through monocular depth priors. However, multi-view constraints become unreliable under large geometric discrepancies, while monocular priors suffer from scale ambiguity and local inconsistency, ultimately leading to inaccurate Gaussian depth supervision. To address these limitations, we introduce a Gaussian visibility-aware multi-view geometric consistency constraint that aggregates the visibility of shared Gaussian primitives across views, enabling more accurate and stable geometric supervision. In addition, we propose a progressive quadtree-calibrated Monocular depth constraint that performs block-wise affine calibration from coarse to fine spatial scales, mitigating the scale ambiguity of depth priors while preserving fine-grained surface details. Extensive experiments on DTU and TNT datasets demonstrate consistent improvements in geometric accuracy over prior Gaussian-based and implicit surface reconstruction methods. Codes are available at an anonymous repository: https://github.com/GVGScode/GVGS.