PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
Top Cited Papers
- 7 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (9) , 6100-6111
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 the proposed method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods. Our code will be made publicly available, and more information can be found on our project page (https://zju3dv.github.io/pgsr/).Keywords
All Related Versions
Funding Information
- NSF of China (61932003)
This publication has 56 references indexed in Scilit:
- Saliency Guided Subdivision for Single-View Mesh Reconstruction2020
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images2018
- Pixelwise View Selection for Unstructured Multi-View Stereo2016
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction2016
- Towards Linear-Time Incremental Structure from Motion2013
- Adaptive Structure from Motion with a Contrario Model Estimation2013
- Fast Normalized Cross-CorrelationCircuits, Systems, and Signal Processing, 2009
- Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo2008
- Delaunay Triangulation Based Surface Reconstruction2006
- A Theory of Shape by Space CarvingInternational Journal of Computer Vision, 2000