Recently, 3D Gaussian Splatting (3DGS) greatly accelerated mesh extraction from posed images due to its explicit representation and fast software rasterization. While the addition of geometric losses and other priors has improved the accuracy of extracted surfaces, mesh extraction remains difficult in scenes with abundant view-dependent effects. To resolve the resulting ambiguities, prior works rely on multi-view techniques, iterative mesh extraction, or large pre-trained models, sacrificing the inherent efficiency of 3DGS. In this work, we present a simple and efficient alternative by introducing a self-supervised confidence framework to 3DGS: within this framework, learnable confidence values dynamically balance photometric and geometric supervision. Extending our confidence-driven formulation, we introduce losses which penalize per-primitive color and normal variance and demonstrate their benefits to surface extraction. Finally, we complement the above with an improved appearance model, by decoupling the individual terms of the D-SSIM loss. Our final approach delivers state-of-the-art results for unbounded meshes while remaining highly efficient.

翻译：最近，三维高斯泼溅（3DGS）凭借其显式表示和快速软件光栅化，极大加速了从姿态图像中的网格提取过程。尽管几何损失函数和先验条件的引入提升了提取表面的精度，但在存在丰富视角依赖效应的场景中，网格提取仍面临困难。为解决由此产生的歧义问题，现有方法依赖多视角技术、迭代网格提取或大型预训练模型，牺牲了3DGS固有的高效性。本文提出一种简单高效的替代方案：通过将自监督置信度框架引入3DGS，在此框架中，可学习的置信度值动态平衡光度监督与几何监督。我们进一步扩展置信度驱动公式，引入惩罚每个图元颜色与法向方差的新损失函数，并论证其对表面提取的益处。最后，通过解耦D-SSIM损失的各项，我们改进了外观模型。最终方法在保持高效性的同时，为无界场景网格提取取得了最先进的结果。