GC-Net: An Unsupervised Network for Gaussian Curvature Optimization on Images

Optimizing Gaussian curvature on images is an important task for image processing. But there is no efficient end-to-end optimization method. Therefore, in this paper, we propose a novel unsupervised network for Gaussian curvature optimization on images, which we named GC-Net. First, we introduce a n...

Full description

Saved in:
Bibliographic Details
Published in:Journal of signal processing systems 2023, Vol.95 (1), p.77-88
Main Authors: Tang, Wenming, Lin, Zewei, Gong, Yuanhao
Format: Article
Language:English
Subjects:
Circuits and Systems
Computer Imaging
Convolution
Curvature
Electrical Engineering
Engineering
Gaussian process
Image processing
Image Processing and Computer Vision
Optimization
Pattern Recognition
Pattern Recognition and Graphics
Regularization
Signal,Image and Speech Processing
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Optimizing Gaussian curvature on images is an important task for image processing. But there is no efficient end-to-end optimization method. Therefore, in this paper, we propose a novel unsupervised network for Gaussian curvature optimization on images, which we named GC-Net. First, we introduce a novel computation scheme for Gaussian curvature on images. The scheme can be presented by several convolutions. Second, we design a cascaded convolution network that is composed by multiple residual convolution blocks. To train this network, we use a loss function which contains image similarity part and Gaussian curvature regularization part. Finally, the proposed network is trained and validated on 20k patches from natural images, showing its effectiveness and efficiency. The GC-Net shows the state of the art performance in minimizing Gaussian curvature. In addition, we conduct rationality experiments to verify the GC-Net architecture design. Moreover, GC-Net is adopted in two well-known image processing tasks, Gaussian curvature optimization and edge-preserving smoothing. Several numerical experiments confirm its efficiency. The proposed GC-Net can be applied in a large range of applications where Gaussian curvature is involved.
ISSN:1939-8018
1939-8115
DOI:10.1007/s11265-022-01800-4