发表机构
Peking University; Pengcheng Laboratory; Beihang University（北京大学; 鹏城实验室; 北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MEGA提出“先分割后网格”框架，利用空间视觉蒸馏和掩码引导神经重建，从3DGS场景提取对象级水密网格，实现准确3D占用并支持物理交互。
AI 中文摘要
从3D高斯泼溅（3DGS）中提取网格旨在赋予3D高斯准确的几何结构，从而实现显式且精确的3D占用。然而，现有方法主要关注场景级网格提取，使其无法表示对象级占用，且常常导致表面非水密。为克服这些限制，我们提出MEGA（从高斯中提取网格），一种“先分割后网格”的框架，用于从复杂的3DGS场景中提取对象级、水密的网格。MEGA的核心是空间视觉蒸馏（SVD）和掩码引导的神经表面重建模块。SVD将3DGS模型视为教师，采样多样化的相机姿态并渲染每个分割对象的对应视图。随后，这些观测通过光度监督用于训练网格重建模型。在多个广泛使用的基准上的大量实验表明，MEGA在恢复准确的对象级3D占用方面达到了最先进的性能。此外，MEGA通过将高质量对象级网格用于几何占用与3DGS表示用于逼真渲染相结合，实现了复杂的物理交互。
英文摘要
Mesh extraction from 3D Gaussian Splatting (3DGS) aims to endow 3D Gaussians with accurate geometric structures, enabling explicit and precise 3D occupancy. However, existing methods primarily focus on scene-level mesh extraction, making them unable to represent object-level occupancy and often resulting in non-watertight surfaces. To overcome these limitations, we propose \textbf{MEGA} (\underline{M}esh \underline{E}xtraction from \underline{GA}ussians), a ``segment-then-mesh'' framework for extracting object-level, watertight meshes from complex 3DGS scenes. At the core of MEGA are \textbf{Spatial Visual Distillation (SVD)} and a mask-guided neural surface reconstruction module. SVD treats the 3DGS model as a teacher, sampling diverse camera poses and rendering the corresponding views of each segmented object. These observations are then used to train a mesh reconstruction model through photometric supervision. Extensive experiments on several widely used benchmarks demonstrate that MEGA achieves state-of-the-art performance in recovering accurate object-level 3D occupancy. Moreover, MEGA enables complex physical interactions by combining high-quality object-level meshes for geometric occupancy with 3DGS representations for photorealistic rendering.
