MILo: 用于精细高效表面重建的网格在环高斯溅射
MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
AI总结：
针对高斯溅射表面重建后处理耗时、细节丢失、网格过密的问题，提出MILo框架，通过可微网格提取等三项技术实现高质量高效重建，网格顶点数较现有方法少一个数量级，适配下游应用。
摘要：
尽管高斯溅射（Gaussian Splatting）的最新进展已实现从图像快速重建高质量3D场景，但提取精确的表面网格仍是一项挑战。现有方法通过耗时的后处理步骤提取表面，会导致精细几何细节丢失，或需要大量时间并生成拥有数百万顶点的极高密度网格。更根本的问题在于，从体积表示到表面表示的后验转换限制了最终网格保留训练过程中捕获的所有几何结构的能力。我们提出MILo，这是一种新颖的高斯溅射框架，通过从3D高斯中可微提取网格，弥合了体积表示与表面表示之间的差距。我们设计了一种完全可微的流程，在每次迭代中直接从高斯参数构建网格（包括顶点位置和连接关系），而高斯参数是训练过程中唯一被优化的量。我们的方法包含三项关键技术贡献：双向一致性框架，确保高斯和提取出的网格这两种表示在训练过程中捕获相同的底层几何结构；在每次训练迭代中执行的自适应网格提取流程，该流程将高斯作为Delaunay三角剖分的可微枢轴；一种从3D高斯计算有符号距离值的新方法，能够在避免几何侵蚀的同时实现精确的表面提取。我们的方法可以重建包括背景在内的完整场景，达到最先进的质量，同时所需的网格顶点数量比以往方法少一个数量级。由于我们的网格重量轻且内部为空，非常适合物理模拟或动画等下游应用。
英文摘要：
While recent advances in Gaussian Splatting have enabled fast reconstruction of high-quality 3D scenes from images, extracting accurate surface meshes remains a challenge. Current approaches extract the surface through costly post-processing steps, resulting in the loss of fine geometric details or requiring significant time and leading to very dense meshes with millions of vertices. More fundamentally, the a posteriori conversion from a volumetric to a surface representation limits the ability of the final mesh to preserve all geometric structures captured during training. We present MILo, a novel Gaussian Splatting framework that bridges the gap between volumetric and surface representations by differentiably extracting a mesh from the 3D Gaussians. We design a fully differentiable procedure that constructs the mesh-including both vertex locations and connectivity-at every iteration directly from the parameters of the Gaussians, which are the only quantities optimized during training. Our method introduces three key technical contributions: a bidirectional consistency framework ensuring both representations-Gaussians and the extracted mesh-capture the same underlying geometry during training; an adaptive mesh extraction process performed at each training iteration, which uses Gaussians as differentiable pivots for Delaunay triangulation; a novel method for computing signed distance values from the 3D Gaussians that enables precise surface extraction while avoiding geometric erosion. Our approach can reconstruct complete scenes, including backgrounds, with state-of-the-art quality while requiring an order of magnitude fewer mesh vertices than previous methods. Due to their light weight and empty interior, our meshes are well suited for downstream applications such as physics simulations or animation.
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。
