Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal

Abstract

In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image. We propose a deep learning approach to predicting the probabilistic distribution of motion blur at the patch level using a convolutional neural network (CNN). We further extend the candidate set of motion kernels predicted by the CNN using carefully designed image rotations. A Markov random field model is then used to infer a dense non-uniform motion blur field enforcing motion smoothness. Finally, motion blur is removed by a non-uniform deblurring model using patch-level image prior. Experimental evaluations show that our approach can effectively estimate and remove complex non-uniform motion blur that is not handled well by previous approaches.

This is a final version accepted by CVPR 2015

Cited by in corpus (12)

• Learning-Based View Synthesis for Light Field Cameras
• Video Frame Interpolation via Adaptive Separable Convolution
• Deep Video Deblurring
• Video Frame Interpolation via Adaptive Convolution
• DeepDeblur: Fast one-step blurry face images restoration
• End-to-End Learning for Image Burst Deblurring
• Learning degraded image classification with restoration data fidelity
• Fiber Orientation Estimation Guided by a Deep Network
• A Deep Optimization Approach for Image Deconvolution
• Human-Aware Motion Deblurring
• Deep Learning for Cornea Microscopy Blind Deblurring
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey