MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation

arXiv:2610.01707v1 Announce Type: new Abstract: 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 extbf{MEGA} (nderline{M}esh nderline{E}xtraction from nderline{GA}ussians), a ``segment-then-mesh'' framework for extracting object-level, watertight meshes from complex 3DGS scenes. At the core of MEGA are extbf{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.

Related

• Confidence-Based Mesh Extraction from 3D Gaussians
• BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
• CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
• StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

Source: arXiv cs.CV | 2026-10-02