Uncertainty-Aware Gaussian Splatting with View-Dependent Regularization for High-Fidelity 3D Reconstruction

3D Gaussian Splatting (3DGS) has emerged as a groundbreaking paradigm for explicit scene representation, achieving photorealistic novel view synthesis with real-time rendering capabilities. However, reconstructing geometrically consistent and accurate surfaces under complex real-world scenarios remains a critical challenge. Current 3DGS frameworks primarily rely on photometric loss optimization, which often results in multi-view geometric inconsistencies and inadequate handling of texture-less regions due to two inherent limitations: 1) the absence of explicit geometric constraints during Gaussian parameter optimization, and 2) the lack of effective mechanisms to resolve multi-view geometric ambiguities. To address these challenges, we propose Uncertainty-Aware Gaussian Splatting (UA-GS), a novel framework that integrates geometric priors with view-dependent uncertainty modeling to explicitly capture and resolve multi-view inconsistencies. For efficient optimization of Gaussian attributes, our approach introduces a spherical harmonics-based uncertainty representation that dynamically models view-dependent geometric variations. Building on this framework, we further design uncertainty-aware optimization strategies. Extensive experiments on real-world and synthetic benchmarks demonstrate that our method significantly outperforms state-of-the-art 3DGS-based approaches in geometric accuracy while retaining competitive rendering quality. Code and data will be made available soon.