arrow
返回

Improved Deep Multi-Patch Hierarchical Network With Nested Module for Dynamic Scene Deblurring

delete2020-01-01
delete10
delete
OA
AI
Z
Zunjin Zhao
B
Bangshu Xiong *
S
Shan Gai
L
Lei Wang
DOI:10.1109/ACCESS.2020.2984002delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Dynamic scene deblurring is a significant technique in the field of computer vision. The multi-scale strategy has been successfully extended to the deep end-to-end learning-based deblurring task. Its expensive computation gives birth to the multi-patch framework. The success of the multi-patch framework benefits from the local residual information passed across the hierarchy. One problem is that the finest levels rarely contribute to their residuals so that the contributions of the finest levels to their residuals are excluded by coarser levels, which limits the deblurring performance. To this end, we substitute the nested module blocks, whose powerful and complex representation ability is utilized to improve the deblurring performance, for the building blocks of the encoder-decoders in the multi-patch network. Additionally, the attention mechanism is introduced to enable the network to differentiate blur across the whole blurry image from dynamic scene, thereby further improving the ability to handle the motion object blur. Our modification boosts the contributions of the finest levels to their residuals and enables the network to learn different weights for feature information extracted from spatially-varying blur image. Extensive experiments show that the improved network achieves competitive performance on the GoPro dataset according to PSNR and SSIM.
Keyword:
Dynamic scene deblurring
multi-patch framework
nested module
attention mechanism
encoder-decoder
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

N
Nanchang Hangkong University
学者数:
7.4K
论文数: 4.0K
被引数: 81
引用论文

引用论文

err
IF0
err
err0
PREAI
err
err分享
err收藏
err分享
err收藏
Job burnout and correlated factors of three‐tiered public health workers: A cross‐sectional study in China
err2020-03-03
err0
errOAAI
errYiqing Mao; Yue Hu; Zhanchun Feng; Ruoxi Wang; Xiaoyu Chen; Weiping Zhang; Gaiying Yang
err分享
err收藏
A Complex Convolution Based Optical Displacement Sensor
err2020-09-24
err0
PREAI
errMatthew Southwick; Zhu Mao; Nicholas A. Valente; Christopher Niezrecki
err分享
err收藏
Lack of autoantibody induction by mercury exposure in artisanal gold mining settings in Colombia: Findings and a review of the epidemiology literature
err2014-12-05
err0
errOAAI
errLuz Helena Sánchez Rodríguez; Oscar Flórez-Vargas; Laura Andrea Rodríguez-Villamizar; Yolanda Vargas Fiallo; Elena E. Stashenko; Gerardo Ramírez
err分享
err收藏
学者 查看更多内容