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

Zunjin Zhao, Bangshu Xiong, Shan Gai, Lei Wang
2020 IEEE Access  
Dynamic scene deblurring is a significant technique in the field of computer vision. The multiscale 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
more » ... 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. INDEX TERMS Dynamic scene deblurring, multi-patch framework, nested module, attention mechanism, encoder-decoder.
doi:10.1109/access.2020.2984002 fatcat:tgtysyk7tba7lgyyjgknxx2hqa