FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiahui, Zhan, Fangneng, Xu, Muyu, Lu, Shijian, Xing, Eric
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911829480964096
author Zhang, Jiahui
Zhan, Fangneng
Xu, Muyu
Lu, Shijian
Xing, Eric
author_facet Zhang, Jiahui
Zhan, Fangneng
Xu, Muyu
Lu, Shijian
Xing, Eric
contents 3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06908
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
Zhang, Jiahui
Zhan, Fangneng
Xu, Muyu
Lu, Shijian
Xing, Eric
Computer Vision and Pattern Recognition
3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
title FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.06908