用置信度动态调节光照与几何监督，提升3D高斯的网格提取精度。
Confidence-Based Mesh Extraction from 3D Gaussians
- 引入可学习置信度，自动平衡光照与几何损失。
- 降低每个高斯点的颜色和法向方差，提升表面一致性。
- 适合追求高效且高质量网格生成的研究者或工程师。
近期，3D高斯泼溅（3DGS）凭借显式表示和快速软件光栅化，显著加速了从姿态图像中提取网格的过程。尽管加入几何损失和其他先验知识已提高表面提取精度，但在存在大量视图依赖效应的场景中，网格提取仍面临模糊性挑战。以往方法依赖多视角技术、迭代提取或大型预训练模型，牺牲了3DGS固有的效率。本文提出一种简单高效的替代方案：在3DGS中引入自监督置信度框架，其中可学习的置信度值动态平衡光度与几何监督。在此框架基础上，我们设计了惩罚每高斯项颜色和法向方差的损失函数，并验证其对表面提取的增益。此外，通过解耦D-SSIM损失中的各项，构建改进的外观模型。最终方法在无界网格提取上达到当前最优性能，同时保持高度效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。