MAStGS: MASt3R-Assisted Efficient 3-D Gaussian Splatting for Indoor Scene Reconstruction
- 1 July 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE MultiMedia
- Vol. 33 (3) , 109-119
Abstract
3D Gaussian Splatting (3DGS) achieves impressive rendering quality, speed, and efficiency but struggles in indoor scenes, especially in textureless or weakly textured regions where geometry is hard to capture accurately. We propose MAStGS, a novel method that marries the strengths of MASt3R with 3DGS to enhance geometric reconstruction in indoor environments. MASt3R provides strong geometric priors but is limited by computational costs. To address this, we segment scenes for efficient MASt3R processing, generate a coarse reconstruction, and align it with COLMAP to initialize 3DGS. A coarse-to-fine training strategy further refines geometry using high-resolution depth and normal supervision. Experiments on indoor datasets show that MAStGS achieves more accurate geometry and higher rendering quality than existing 3DGS methods.Keywords
This publication has 17 references indexed in Scilit:
- GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction2025
- 360-GS: Layout-Guided Panoramic Gaussian Splatting for Indoor Roaming2025
- Grounding Image Matching in 3D with MASt3R2024
- Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering2024
- Mip-Splatting: Alias-Free 3D Gaussian Splatting2024
- ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes2023
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Structure-from-Motion Revisited2016
- The Weiszfeld Algorithm: Proof, Amendments, and Extensions2011
- Least-squares estimation of transformation parameters between two point patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991