Deblurring Images via Dark Channel Prior

We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 40; no. 10; pp. 2315 - 2328
Main Authors: Pan, Jinshan, Sun, Deqing, Pfister, Hanspeter, Yang, Ming-Hsuan
Format: Journal Article
Language:English
Published: United States IEEE 01.10.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithm design and analysis
Algorithms
Convolution
dark channel prior
Face
Image deblurring
Image edge detection
Image restoration
Kernel
linear approximation
non-uniform deblurring
Optimization
Pixels
Sparsity
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2017.2753804