PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

TL;DR

This paper introduces PGSR, a planar-based Gaussian splatting method that achieves high-fidelity surface reconstruction with fast training and rendering, addressing limitations of previous 3D Gaussian Splatting techniques.

Contribution

The paper proposes a novel planar-based Gaussian splatting representation with an unbiased depth rendering method and regularization techniques for improved geometric accuracy.

Findings

Outperforms existing 3DGS and NeRF methods in quality and speed.

Achieves high-fidelity surface reconstruction in indoor and outdoor scenes.

Ensures multi-view consistency and handles illumination variations effectively.

Abstract

Recently, 3D Gaussian Splatting (3DGS) has attracted widespread attention due to its high-quality rendering, and ultra-fast training and rendering speed. However, due to the unstructured and irregular nature of Gaussian point clouds, it is difficult to guarantee geometric reconstruction accuracy and multi-view consistency simply by relying on image reconstruction loss. Although many studies on surface reconstruction based on 3DGS have emerged recently, the quality of their meshes is generally unsatisfactory. To address this problem, we propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction while ensuring high-quality rendering. Specifically, we first introduce an unbiased depth rendering method, which directly renders the distance from the camera origin to the Gaussian plane and the corresponding normal map based on the Gaussian distribution of the point cloud, and divides the two to obtain the unbiased depth. We then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy. We also propose a camera exposure compensation model to cope with scenes with large illumination variations. Experiments on indoor and outdoor scenes show that our method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods.