FormNet: Formatted Learning for Image Restoration

Jianbo Jiao

doi:10.1109/TIP.2020.2990603

FormNet: Formatted Learning for Image Restoration

2020-01-01

16

PRE

AI

DOI：10.1109/TIP.2020.2990603

原文链接

原文求助

摘要

En 中文

In this paper, we propose a deep CNN to tackle the image restoration problem by learning formatted information. Previous deep learning based methods directly learn the mapping from corrupted images to clean images, and may suffer from the gradient exploding/vanishing problems of deep neural networks. We propose to address the image restoration problem by learning the structured details and recovering the latent clean image together, from the shared information between the corrupted image and the latent image. In addition, instead of learning the pure difference (corruption), we propose to add a residual formatting layer and an adversarial block to format the information to structured one, which allows the network to converge faster and boosts the performance. Furthermore, we propose a cross-level loss net to ensure both pixel-level accuracy and semantic-level visual quality. Evaluations on public datasets show that the proposed method performs favorably against existing approaches quantitatively and qualitatively.

Keyword:

Image restoration

format

residual

GAN

CNN

FormNet: Formatted Learning for Image Restoration

摘要

AI总结

期刊

机构