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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Danpeng, Li, Hai, Ye, Weicai, Wang, Yifan, Xie, Weijian, Zhai, Shangjin, Wang, Nan, Liu, Haomin, Bao, Hujun, Zhang, Guofeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912182474637312
author Chen, Danpeng
Li, Hai
Ye, Weicai
Wang, Yifan
Xie, Weijian
Zhai, Shangjin
Wang, Nan
Liu, Haomin
Bao, Hujun
Zhang, Guofeng
author_facet Chen, Danpeng
Li, Hai
Ye, Weicai
Wang, Yifan
Xie, Weijian
Zhai, Shangjin
Wang, Nan
Liu, Haomin
Bao, Hujun
Zhang, Guofeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06521
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
Chen, Danpeng
Li, Hai
Ye, Weicai
Wang, Yifan
Xie, Weijian
Zhai, Shangjin
Wang, Nan
Liu, Haomin
Bao, Hujun
Zhang, Guofeng
Computer Vision and Pattern Recognition
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.
title PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.06521