Motion deblurring for noisy and blurry images is an arduous and fundamental problem in image processing community. The problem is ill-posed as many different pairs of latent image and blur kernel can render the same blurred image, and thus, the optimization of this problem is still unsolved. To tackle it, we present an effective motion deblurring method for noisy and blurry images based on prominent structure and a data-driven heavy-tailed prior of enhanced gradient. Specifically, first, we employ denoising as a preprocess to remove the input image noise, and then restore strong edges for accurate kernel estimation. The image extreme channels-based priors (dark channel prior and bright channel prior) as sparse complementary knowledge are exploited to extract prominent structure. High closeness of the extracted structure to the clear image structure can be obtained via tuning the parameters of extraction function. Next, the integration term of enhanced interim image gradient and clear image heavy-tailed prior is proposed and then embedded into the image restoration model, which favors sharp images over blurry ones. A large number of experiments on both synthetic and real-life images verify the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively.
Hongtian ZHAO
Shanghai Jiao Tong University
Shibao ZHENG
Shanghai Jiao Tong University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hongtian ZHAO, Shibao ZHENG, "Joint Extreme Channels-Inspired Structure Extraction and Enhanced Heavy-Tailed Priors Heuristic Kernel Estimation for Motion Deblurring of Noisy and Blurry Images" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 12, pp. 1520-1528, December 2020, doi: 10.1587/transfun.2020SMP0008.
Abstract: Motion deblurring for noisy and blurry images is an arduous and fundamental problem in image processing community. The problem is ill-posed as many different pairs of latent image and blur kernel can render the same blurred image, and thus, the optimization of this problem is still unsolved. To tackle it, we present an effective motion deblurring method for noisy and blurry images based on prominent structure and a data-driven heavy-tailed prior of enhanced gradient. Specifically, first, we employ denoising as a preprocess to remove the input image noise, and then restore strong edges for accurate kernel estimation. The image extreme channels-based priors (dark channel prior and bright channel prior) as sparse complementary knowledge are exploited to extract prominent structure. High closeness of the extracted structure to the clear image structure can be obtained via tuning the parameters of extraction function. Next, the integration term of enhanced interim image gradient and clear image heavy-tailed prior is proposed and then embedded into the image restoration model, which favors sharp images over blurry ones. A large number of experiments on both synthetic and real-life images verify the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020SMP0008/_p
Copy
@ARTICLE{e103-a_12_1520,
author={Hongtian ZHAO, Shibao ZHENG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Joint Extreme Channels-Inspired Structure Extraction and Enhanced Heavy-Tailed Priors Heuristic Kernel Estimation for Motion Deblurring of Noisy and Blurry Images},
year={2020},
volume={E103-A},
number={12},
pages={1520-1528},
abstract={Motion deblurring for noisy and blurry images is an arduous and fundamental problem in image processing community. The problem is ill-posed as many different pairs of latent image and blur kernel can render the same blurred image, and thus, the optimization of this problem is still unsolved. To tackle it, we present an effective motion deblurring method for noisy and blurry images based on prominent structure and a data-driven heavy-tailed prior of enhanced gradient. Specifically, first, we employ denoising as a preprocess to remove the input image noise, and then restore strong edges for accurate kernel estimation. The image extreme channels-based priors (dark channel prior and bright channel prior) as sparse complementary knowledge are exploited to extract prominent structure. High closeness of the extracted structure to the clear image structure can be obtained via tuning the parameters of extraction function. Next, the integration term of enhanced interim image gradient and clear image heavy-tailed prior is proposed and then embedded into the image restoration model, which favors sharp images over blurry ones. A large number of experiments on both synthetic and real-life images verify the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively.},
keywords={},
doi={10.1587/transfun.2020SMP0008},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - Joint Extreme Channels-Inspired Structure Extraction and Enhanced Heavy-Tailed Priors Heuristic Kernel Estimation for Motion Deblurring of Noisy and Blurry Images
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1520
EP - 1528
AU - Hongtian ZHAO
AU - Shibao ZHENG
PY - 2020
DO - 10.1587/transfun.2020SMP0008
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2020
AB - Motion deblurring for noisy and blurry images is an arduous and fundamental problem in image processing community. The problem is ill-posed as many different pairs of latent image and blur kernel can render the same blurred image, and thus, the optimization of this problem is still unsolved. To tackle it, we present an effective motion deblurring method for noisy and blurry images based on prominent structure and a data-driven heavy-tailed prior of enhanced gradient. Specifically, first, we employ denoising as a preprocess to remove the input image noise, and then restore strong edges for accurate kernel estimation. The image extreme channels-based priors (dark channel prior and bright channel prior) as sparse complementary knowledge are exploited to extract prominent structure. High closeness of the extracted structure to the clear image structure can be obtained via tuning the parameters of extraction function. Next, the integration term of enhanced interim image gradient and clear image heavy-tailed prior is proposed and then embedded into the image restoration model, which favors sharp images over blurry ones. A large number of experiments on both synthetic and real-life images verify the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively.
ER -