DenoiseGS: Gaussian Reconstruction Model for Burst Denoising

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Yongsen, Cai, Yuanhao, Zhang, Yulun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911296008486912
author Cheng, Yongsen
Cai, Yuanhao
Zhang, Yulun
author_facet Cheng, Yongsen
Cai, Yuanhao
Zhang, Yulun
contents Burst denoising methods are crucial for enhancing images captured on handheld devices, but they often struggle with large motion or suffer from prohibitive computational costs. In this paper, we propose DenoiseGS, the first framework to leverage the efficiency of 3D Gaussian Splatting for burst denoising. Our approach addresses two key challenges when applying feedforward Gaussian reconsturction model to noisy inputs: the degradation of Gaussian point clouds and the loss of fine details. To this end, we propose a Gaussian self-consistency (GSC) loss, which regularizes the geometry predicted from noisy inputs with high-quality Gaussian point clouds. These point clouds are generated from clean inputs by the same model that we are training, thereby alleviating potential bias or domain gaps. Additionally, we introduce a log-weighted frequency (LWF) loss to strengthen supervision within the spectral domain, effectively preserving fine-grained details. The LWF loss adaptively weights frequency discrepancies in a logarithmic manner, emphasizing challenging high-frequency details. Extensive experiments demonstrate that DenoiseGS significantly exceeds the state-of-the-art NeRF-based methods on both burst denoising and novel view synthesis under noisy conditions, while achieving 250$\times$ faster inference speed. Code and models are released at https://github.com/yscheng04/DenoiseGS.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
Cheng, Yongsen
Cai, Yuanhao
Zhang, Yulun
Computer Vision and Pattern Recognition
Burst denoising methods are crucial for enhancing images captured on handheld devices, but they often struggle with large motion or suffer from prohibitive computational costs. In this paper, we propose DenoiseGS, the first framework to leverage the efficiency of 3D Gaussian Splatting for burst denoising. Our approach addresses two key challenges when applying feedforward Gaussian reconsturction model to noisy inputs: the degradation of Gaussian point clouds and the loss of fine details. To this end, we propose a Gaussian self-consistency (GSC) loss, which regularizes the geometry predicted from noisy inputs with high-quality Gaussian point clouds. These point clouds are generated from clean inputs by the same model that we are training, thereby alleviating potential bias or domain gaps. Additionally, we introduce a log-weighted frequency (LWF) loss to strengthen supervision within the spectral domain, effectively preserving fine-grained details. The LWF loss adaptively weights frequency discrepancies in a logarithmic manner, emphasizing challenging high-frequency details. Extensive experiments demonstrate that DenoiseGS significantly exceeds the state-of-the-art NeRF-based methods on both burst denoising and novel view synthesis under noisy conditions, while achieving 250$\times$ faster inference speed. Code and models are released at https://github.com/yscheng04/DenoiseGS.
title DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22939