Down-Scaling with Learned Kernels in Multi-Scale Deep Neural Networks for Non-Uniform Single Image Deblurring

by   Dongwon Park, et al.

Multi-scale approach has been used for blind image / video deblurring problems to yield excellent performance for both conventional and recent deep-learning-based state-of-the-art methods. Bicubic down-sampling is a typical choice for multi-scale approach to reduce spatial dimension after filtering with a fixed kernel. However, this fixed kernel may be sub-optimal since it may destroy important information for reliable deblurring such as strong edges. We propose convolutional neural network (CNN)-based down-scale methods for multi-scale deep-learning-based non-uniform single image deblurring. We argue that our CNN-based down-scaling effectively reduces the spatial dimension of the original image, while learned kernels with multiple channels may well-preserve necessary details for deblurring tasks. For each scale, we adopt to use RCAN (Residual Channel Attention Networks) as a backbone network to further improve performance. Our proposed method yielded state-of-the-art performance on GoPro dataset by large margin. Our proposed method was able to achieve 2.59dB higher PSNR than the current state-of-the-art method by Tao. Our proposed CNN-based down-scaling was the key factor for this excellent performance since the performance of our network without it was decreased by 1.98dB. The same networks trained with GoPro set were also evaluated on large-scale Su dataset and our proposed method yielded 1.15dB better PSNR than the Tao's method. Qualitative comparisons on Lai dataset also confirmed the superior performance of our proposed method over other state-of-the-art methods.


page 1

page 3

page 4

page 6

page 7

page 8


MUSIQ: Multi-scale Image Quality Transformer

Image quality assessment (IQA) is an important research topic for unders...

Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training

Multi-scale (MS) approaches have been widely investigated for blind sing...

SR-R^2KAC: Improving Single Image Defocus Deblurring

We propose an efficient deep learning method for single image defocus de...

Super-Resolution with Deep Adaptive Image Resampling

Deep learning based methods have recently pushed the state-of-the-art on...

Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing

Recently, CNN based end-to-end deep learning methods achieve superiority...

Deep Vessel Segmentation By Learning Graphical Connectivity

We propose a novel deep-learning-based system for vessel segmentation. E...

Analysis of CNN-based remote-PPG to understand limitations and sensitivities

Deep learning based on convolutional neural network (CNN) has shown prom...

Please sign up or login with your details

Forgot password? Click here to reset