DeepAI AI Chat
Log In Sign Up

Edge Prior Augmented Networks for Motion Deblurring on Naturally Blurry Images

by   Yuedong Chen, et al.
University of Oxford
Monash University

Motion deblurring has witnessed rapid development in recent years, and most of the recent methods address it by using deep learning techniques, with the help of different kinds of prior knowledge. Concerning that deblurring is essentially expected to improve the image sharpness, edge information can serve as an important prior. However, the edge has not yet been seriously taken into consideration in previous methods when designing deep models. To this end, we present a novel framework that incorporates edge prior knowledge into deep models, termed Edge Prior Augmented Networks (EPAN). EPAN has a content-based main branch and an edge-based auxiliary branch, which are constructed as a Content Deblurring Net (CDN) and an Edge Enhancement Net (EEN), respectively. EEN is designed to augment CDN in the deblurring process via an attentive fusion mechanism, where edge features are mapped as spatial masks to guide content features in a feature-based hierarchical manner. An edge-guided loss function is proposed to further regulate the optimization of EPAN by enforcing the focus on edge areas. Besides, we design a dual-camera-based image capturing setting to build a new dataset, Real Object Motion Blur (ROMB), with paired sharp and naturally blurry images of fast-moving cars, so as to better train motion deblurring models and benchmark the capability of motion deblurring algorithms in practice. Extensive experiments on the proposed ROMB and other existing datasets demonstrate that EPAN outperforms state-of-the-art approaches qualitatively and quantitatively.


page 1

page 3

page 6

page 8

page 9


Non-uniform Motion Deblurring with Blurry Component Divided Guidance

Blind image deblurring is a fundamental and challenging computer vision ...

Edge Heuristic GAN for Non-uniform Blind Deblurring

Non-uniform blur, mainly caused by camera shake and motions of multiple ...

Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets

We propose a fusion algorithm for haze removal that combines color infor...

From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

Removing pixel-wise heterogeneous motion blur is challenging due to the ...

Minimum Latency Deep Online Video Stabilization

We present a novel camera path optimization framework for the task of on...

Disentangling Content and Style via Unsupervised Geometry Distillation

It is challenging to disentangle an object into two orthogonal spaces of...

Code Repositories