MPP-GS: Multi-Granularity Planar Prior Guided Gaussian Splatting for Indoor Scene Reconstruction
TL;DR
This work proposes a planar prior guided 3D Gaussian Splatting framework for indoor scene reconstruction, and incorporates region-aware geometric optimization into the 3DGS pipeline, including planar region constraints, non-planar local geometric regularization, and global geometry supervision to jointly improve structural fidelity and surface consistency.
Abstract
3D Gaussian Splatting (3DGS) has recently achieved impressive performance in novel view synthesis and real-time rendering. However, its geometric reconstruction quality in indoor scenes remains limited, especially in large weak-texture regions such as walls, ceilings, and floors, where sparse initialization and purely photometric supervision often lead to floaters, distorted surfaces, and structural ambiguities. To address this issue, we propose a planar prior guided 3D Gaussian Splatting framework for indoor scene reconstruction. Our method first extracts dense geometric priors, including depth and normal maps, from input images to provide robust structural guidance for optimization. Based on these priors, we further construct planar priors through multi-granularity image segmentation and geometric consistency verification, enabling reliable identification of planar regions in complex indoor scenes. We then incorporate region-aware geometric optimization into the 3DGS pipeline, including planar region constraints, non-planar local geometric regularization, and global geometry supervision, to jointly improve structural fidelity and surface consistency. Extensive experiments on multiple indoor datasets demonstrate that the proposed method produces more accurate meshes and more faithful rendering results than recent 3DGS-based baselines, particularly in weak-texture and piecewise-planar areas.