2DGS-Room: Seed-Guided 2D Gaussian Splatting with Geometric Constrains for High-Fidelity Indoor Scene Reconstruction

TL;DR

This work addresses indoor scene reconstruction by extending 2D Gaussian Splatting with a seed-guided mechanism that aligns Gaussian distributions to scene structure. It introduces adaptive seed growth/pruning, monocular depth and normal priors, and multi-view consistency to enforce geometric and photometric coherence across views. The approach achieves state-of-the-art surface reconstruction on ScanNet and ScanNet++ while offering substantial speed advantages over neural-volume methods. These advances yield clearer geometry in textureless regions and more reliable indoor scene reconstructions with practical implications for robotics, AR/VR, and visualization.

Abstract

The reconstruction of indoor scenes remains challenging due to the inherent complexity of spatial structures and the prevalence of textureless regions. Recent advancements in 3D Gaussian Splatting have improved novel view synthesis with accelerated processing but have yet to deliver comparable performance in surface reconstruction. In this paper, we introduce 2DGS-Room, a novel method leveraging 2D Gaussian Splatting for high-fidelity indoor scene reconstruction. Specifically, we employ a seed-guided mechanism to control the distribution of 2D Gaussians, with the density of seed points dynamically optimized through adaptive growth and pruning mechanisms. To further improve geometric accuracy, we incorporate monocular depth and normal priors to provide constraints for details and textureless regions respectively. Additionally, multi-view consistency constraints are employed to mitigate artifacts and further enhance reconstruction quality. Extensive experiments on ScanNet and ScanNet++ datasets demonstrate that our method achieves state-of-the-art performance in indoor scene reconstruction.

Figures (10)

• Figure 1: 2DGS-Room achieves high-fidelity geometric reconstructions for indoor scenes. We introduce seed points to guide the distribution of 2D Gaussians coupled with geometric constraints, leading to clearer structures and more accurate geometry.
• Figure 2: Overview of 2DGS-Room. Given multi-view posed images, we improve 2DGS to achieve high-fidelity geometric reconstruction for indoor scenes. (a) Starting from an SfM-derived point cloud, we generate a set of seed points through voxelization, establishing a stable foundation for guiding the distribution and density of 2D Gaussians. We further introduce an adaptive growth and pruning strategy to optimize seed points. (b) We incorporate depth and normal priors, addressing the challenges of detailed areas and textureless regions. (c) We introduce multi-view consistency constraints to further enhance the quality of the indoor scene reconstruction.
• Figure 3: Ground truth scene surface and Gaussian primitives distribution. Compared with 3DGS and 2DGS, our method significantly reduces scattered floaters in the non-surface areas, benefitting from our designed structured geometric constraints.
• Figure 4: Qualitative reconstruction comparisons. For each indoor scene, the first row is the top view of the whole room, and the second row is the details of the masked region.
• Figure 5: Qualitative results of ablation study.