.png){kind=icon}
返回
Gaussian error loss function for image smoothing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2024.105300.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Edge-preserving image smoothing plays an important role in the fields of image processing and computational photography, and is widely used for a variety of applications. The edge-preserving filters based on global optimization models have attracted widespread attention due to their nice smoothing quality. According to existing research, the edge-preserving capability is strongly correlated to the penalty function used for gradient regularization. By analyzing the edge-stopping function of existing penalties, we demonstrate that existing image smoothing models are not adequately edge-preserving. In this paper, based on a Gaussian error function (ERF), we propose a Gaussian error loss function (ERLF), which shows stronger edge-preserving capability. We embed the proposed loss function into a global optimization model for edge-preserving image smoothing. In addition, we propose an efficient solution based on additive half-quadratic minimization and Fourier-domain optimization that is capable of processing 720P color images (over 20 fps) in real-time on an NVIDIA RTX 3070 GPU. We have experimented with the proposed filter on a number of low-level vision tasks. Both quantitative and qualitative experimental results show that the proposed filter outperforms existing filters. Therefore, it can be practical for real applications.
Keyword:
Loss function
Edge-preserving
Image smoothing
Global optimization
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
.png){kind=icon}
Prevalence of aortic valve abnormalities in the elderly: An echocardiographic study of a random population sample老年人主动脉瓣异常的患病率: 随机人群样本的超声心动图研究
PREAI
分享收藏Easy2Hard: Learning to Solve the Intractables From a Synthetic Dataset for Structure-Preserving Image SmoothingEasy2Hard: 学习从合成数据集中解决难题，以保持结构的图像平滑
PREAI
分享收藏
查看更多内容