用于稀疏图像序列表面重建的不确定性感知法线引导高斯泼溅
Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequences
AI总结：
针对稀疏图像序列中3DGS几何不确定性导致的结构伪影问题，提出UNG-GS框架，通过空间不确定性场、不确定性感知深度渲染和法线细化实现无先验的高保真重建。
摘要：
3D Gaussian Splatting（3DGS，三维高斯泼溅）在新视角合成中取得了令人瞩目的渲染性能。然而，在稀疏图像序列中，其有效性会显著下降，因为固有的数据稀疏性会放大优化过程中的几何不确定性。这往往导致模型收敛到次优局部极小值，使重建场景出现明显的结构伪影。为缓解这些问题，我们提出了不确定性感知法线引导高斯泼溅（Uncertainty-aware Normal-Guided Gaussian Splatting，UNG-GS），这是一种新颖框架，其特点是通过显式的空间不确定性场（Spatial Uncertainty Field，SUF）来量化3DGS流程中的几何不确定性。UNG-GS无需依赖先验即可实现高保真渲染和高精度重建。具体而言，我们首先将基于高斯的概率建模集成到3DGS训练中以优化SUF，从而为模型提供自适应误差容限。随后采用不确定性感知深度渲染策略，根据SUF对深度贡献进行加权，在保留精细细节的同时有效降低噪声。此外，不确定性引导的法线细化方法会在法线估计中调整相邻深度值的影响，从而提升结果的鲁棒性。大量实验表明，UNG-GS在稀疏和稠密序列上均显著优于最先进方法。代码将开源。
英文摘要：
3D Gaussian Splatting (3DGS) has achieved impressive rendering performance in novel view synthesis. However, its efficacy diminishes considerably in sparse image sequences, where inherent data sparsity amplifies geometric uncertainty during optimization. This often leads to convergence at suboptimal local minima, resulting in noticeable structural artifacts in the reconstructed scenes.To mitigate these issues, we propose Uncertainty-aware Normal-Guided Gaussian Splatting (UNG-GS), a novel framework featuring an explicit Spatial Uncertainty Field (SUF) to quantify geometric uncertainty within the 3DGS pipeline. UNG-GS enables high-fidelity rendering and achieves high-precision reconstruction without relying on priors. Specifically, we first integrate Gaussian-based probabilistic modeling into the training of 3DGS to optimize the SUF, providing the model with adaptive error tolerance. An uncertainty-aware depth rendering strategy is then employed to weight depth contributions based on the SUF, effectively reducing noise while preserving fine details. Furthermore, an uncertainty-guided normal refinement method adjusts the influence of neighboring depth values in normal estimation, promoting robust results. Extensive experiments demonstrate that UNG-GS significantly outperforms state-of-the-art methods in both sparse and dense sequences. The code will be open-source.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
