Deep Dynamic Scene Deblurring from Optical Flow

by   Jiawei Zhang, et al.

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a non-trivial task as it is difficult to model the non-uniform blur mathematically. Several methods first use single or multiple images to estimate optical flow (which is treated as an approximation of blur kernels) and then adopt non-blind deblurring algorithms to reconstruct the sharp images. However, these methods cannot be trained in an end-to-end manner and are usually computationally expensive. In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN). We utilize FlowNets to estimate optical flow from two consecutive images in different scales. The estimated optical flow provides the RNN weights in different scales so that the weights can better help RNNs to remove blur in the feature spaces. Finally, we develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size.


page 1

page 3

page 6

page 8

page 9

page 11


Spatio-Temporal Filter Adaptive Network for Video Deblurring

Video deblurring is a challenging task due to the spatially variant blur...

OmniFlow: Human Omnidirectional Optical Flow

Optical flow is the motion of a pixel between at least two consecutive v...

Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

Non-uniform blind deblurring for general dynamic scenes is a challenging...

Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Model

State-of-the-art video deblurring methods cannot handle blurry videos re...

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior

We present a simple and effective deep convolutional neural network (CNN...

A Theory for Optical flow-based Transport on Image Manifolds

An image articulation manifold (IAM) is the collection of images formed ...

Microscopic Muscle Image Enhancement

We propose a robust image enhancement algorithm dedicated for muscle fib...

Please sign up or login with your details

Forgot password? Click here to reset