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 \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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liao, L., Zhang, Y., Tong, Q., & Wang, R. (2026). MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation. https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation
MLA 9
Liao, Liwei, et al. "MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation." https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation.
Chicago (author–date)
Liao, Liwei, Yingkui Zhang, Qianqian Tong, and Ronggang Wang. 2026. "MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation." https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation.
Harvard
Liao, L., Zhang, Y., Tong, Q. and Wang, R. (2026) 'MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation', Available at: https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation.
Vancouver
Liao L, Zhang Y, Tong Q, Wang R. MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation. https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation
IEEE
L. Liao, Y. Zhang, Q. Tong, and R. Wang, "MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation," https://omanscience.com/en/articles/mega-object-level-mesh-extraction-from-3d-gaussian-splatting-via-spatial-visual-distillation.