Rank-One Network: An Effective Framework for Image Restoration

by   Shangqi Gao, et al.

The principal rank-one (RO) components of an image represent the self-similarity of the image, which is an important property for image restoration. However, the RO components of a corrupted image could be decimated by the procedure of image denoising. We suggest that the RO property should be utilized and the decimation should be avoided in image restoration. To achieve this, we propose a new framework comprised of two modules, i.e., the RO decomposition and RO reconstruction. The RO decomposition is developed to decompose a corrupted image into the RO components and residual. This is achieved by successively applying RO projections to the image or its residuals to extract the RO components. The RO projections, based on neural networks, extract the closest RO component of an image. The RO reconstruction is aimed to reconstruct the important information, respectively from the RO components and residual, as well as to restore the image from this reconstructed information. Experimental results on four tasks, i.e., noise-free image super-resolution (SR), realistic image SR, gray-scale image denoising, and color image denoising, show that the method is effective and efficient for image restoration, and it delivers superior performance for realistic image SR and color image denoising.


page 2

page 5

page 16

page 20

page 21

page 24


Constrained low-rank quaternion approximation for color image denoising by bilateral random projections

In this letter, we propose a novel low-rank quaternion approximation (LR...

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Discriminative model learning for image denoising has been recently attr...

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

Ever since the advent of AlexNet, designing novel deep neural architectu...

Functional Neural Networks for Parametric Image Restoration Problems

Almost every single image restoration problem has a closely related para...

Multi-bin Trainable Linear Unit for Fast Image Restoration Networks

Tremendous advances in image restoration tasks such as denoising and sup...

U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

This paper studies the challenging problem of fingerprint image denoisin...

Structured Uncertainty Prediction Networks

This paper is the first work to propose a network to predict a structure...

Please sign up or login with your details

Forgot password? Click here to reset