Saved in:
Bibliographic Details
Main Authors: Zeng, Zhaojie, Wang, Yuesong, Ju, Lili, Guan, Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07000
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929751344545792
author Zeng, Zhaojie
Wang, Yuesong
Ju, Lili
Guan, Tao
author_facet Zeng, Zhaojie
Wang, Yuesong
Ju, Lili
Guan, Tao
contents By adaptively controlling the density and generating more Gaussians in regions with high-frequency information, 3D Gaussian Splatting (3DGS) can better represent scene details. From the signal processing perspective, representing details usually needs more Gaussians with relatively smaller scales. However, 3DGS currently lacks an explicit constraint linking the density and scale of 3D Gaussians across the domain, leading to 3DGS using improper-scale Gaussians to express frequency information, resulting in the loss of accuracy. In this paper, we propose to establish a direct relation between density and scale through the reparameterization of the scaling parameters and ensure the consistency between them via explicit constraints (i.e., density responds well to changes in frequency). Furthermore, we develop a frequency-aware density control strategy, consisting of densification and deletion, to improve representation quality with fewer Gaussians. A dynamic threshold encourages densification in high-frequency regions, while a scale-based filter deletes Gaussians with improper scale. Experimental results on various datasets demonstrate that our method outperforms existing state-of-the-art methods quantitatively and qualitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07000
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting
Zeng, Zhaojie
Wang, Yuesong
Ju, Lili
Guan, Tao
Computer Vision and Pattern Recognition
By adaptively controlling the density and generating more Gaussians in regions with high-frequency information, 3D Gaussian Splatting (3DGS) can better represent scene details. From the signal processing perspective, representing details usually needs more Gaussians with relatively smaller scales. However, 3DGS currently lacks an explicit constraint linking the density and scale of 3D Gaussians across the domain, leading to 3DGS using improper-scale Gaussians to express frequency information, resulting in the loss of accuracy. In this paper, we propose to establish a direct relation between density and scale through the reparameterization of the scaling parameters and ensure the consistency between them via explicit constraints (i.e., density responds well to changes in frequency). Furthermore, we develop a frequency-aware density control strategy, consisting of densification and deletion, to improve representation quality with fewer Gaussians. A dynamic threshold encourages densification in high-frequency regions, while a scale-based filter deletes Gaussians with improper scale. Experimental results on various datasets demonstrate that our method outperforms existing state-of-the-art methods quantitatively and qualitatively.
title Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.07000