FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
Authors:
Top Cited Papers
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21424-21433
Abstract
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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- TensoRF: Tensorial Radiance Fields2022
- Plenoxels: Radiance Fields without Neural Networks2022
- Dynamic View Synthesis from Dynamic Monocular Video2021
- AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis2021
- BARF: Bundle-Adjusting Neural Radiance Fields2021
- Free View Synthesis2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Escaping Plato’s Cave: 3D Shape From Adversarial Rendering2019
- Structure-from-Motion Revisited2016
- Multiple View Geometry in Computer Vision2004