Deep Ranking Exemplar-Based Dynamic Scene Deblurring

doi:10.1109/TIP.2022.3142518

2022-01-01

PRE

Li, Yaowei

Jinshan Pan (Jinshan Pan)

罗烨 (Ye Luo)

Jianwei Lu *

DOI：10.1109/TIP.2022.3142518

原文链接

原文求助

摘要

En 中文

Dynamic scene deblurring is a challenging problem as it is difficult to be modeled mathematically. Benefiting from the deep convolutional neural networks, this problem has been significantly advanced by the end-to-end network architectures. However, the success of these methods is mainly due to simply stacking network layers. In addition, the methods based on the end-to-end network architectures usually estimate latent images in a regression way which does not preserve the structural details. In this paper, we propose an exemplar-based method to solve dynamic scene deblurring problem. To explore the properties of the exemplars, we propose a siamese encoder network and a shallow encoder network to respectively extract input features and exemplar features and then develop a rank module to explore useful features for better blur removing, where the rank modules are applied to the last three layers of encoder, respectively. The proposed method can be further extended to the way of multi-scale, which enables to recover more texture from the exemplar. Extensive experiments show that our method achieves significant improvements in both quantitative and qualitative evaluations.

Keyword:

Image restoration

Feature extraction

Correlation

Kernel

Superresolution

Task analysis

Convolutional neural networks

Image deblurring

exemplar

deep convolutional neural networks