Motion deblurring using edge map with blurred/noisy image pairs

Lee, Ser-Hoon; Park, Hyung‐Min; Hwang, Sung Yeon

doi:10.1016/j.optcom.2011.12.057

Cited by 15 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in most cases, the discrepancy problem cannot be ignored, and thus, more sophisticated techniques are required. One solution is to adopt a regularization approach [3,6,7] that has been widely used for image-pair-based restoration. The regularization term can be modeled as follows:…”

Section: A Regularization Approachmentioning

confidence: 99%

“…It is guessed that the main reason is due to the non-Gaussian noise in the captured visible color image. The image-pair-based denoising methods based on the weighted least squares [2] and gradient regularization [3,6,7] can produce better-resulting images than those obtained from the BM3D. This is possible because the clean near-infrared image is used as a guidance image [2].…”

Section: Detail Layer Transfermentioning

confidence: 99%

“…The experimental results show that the proposed approach used for the near-infrared coloring can also be applied to image pairs captured under dim lighting conditions. Moreover, it is discussed how the proposed near-infrared denoising differs from conventional image-pair-based fusion [2,3,6,7,8,9,10].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Son

Zhang

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Section: A Regularization Approachmentioning

confidence: 99%

Section: Detail Layer Transfermentioning

confidence: 99%

See 1 more Smart Citation

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Son

Zhang

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

“…Table 2 shows the (hand-optimized) best values of λ 1 and λ 2 (in terms of PSNR) in Prob. (12) for each test image, where the regularization term was set to the color TV. For every test image, the noise standard deviations of a for all the test images, i.e., the parameter setting is much easier.…”

Section: Facilitation Of Parameter Settingmentioning

confidence: 99%

Image Restoration with Multiple Hard Constraints on Data-Fidelity to Blurred/Noisy Image Pair

Takeyama¹,

Ono

Kumazawa

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYExisting image deblurring methods with a blurred/noisy image pair take a two-step approach: blur kernel estimation and image restoration. They can achieve better and much more stable blur kernel estimation than single image deblurring methods. On the other hand, in the image restoration step, they do not exploit the information on the noisy image, or they require ad hoc tuning of interdependent parameters. This paper focuses on the image restoration step and proposes a new restoration method of using a blurred/noisy image pair. In our method, the image restoration problem is formulated as a constrained convex optimization problem, where data-fidelity to a blurred image and that to a noisy image is properly taken into account as multiple hard constraints. This offers (i) high quality restoration when the blurred image also contains noise; (ii) robustness to the estimation error of the blur kernel; and (iii) easy parameter setting. We also provide an efficient algorithm for solving our optimization problem based on the so-called alternating direction method of multipliers (ADMM). Experimental results support our claims.

show abstract

“…Yuan et al [15] first uses a wavelet-based denoising algorithm to restore the noisy image, and then estimates the blur kernel based on the denoised image, finally uses Richardson-Lucy(RL) algorithm to restore image. Lee et al [16] uses fast bilateral filtering to restore the noisy image, then estimates the blur kernel based on the gradient of the denoised image, and finally restores the image combining with the denoised image and a hyper-Laplacian prior.…”

Section: Introductionmentioning

confidence: 99%

Joint Motion Deblurring with Blurred/Noisy Image Pair

Zhang

Sun

et al. 2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Motion blurred images are widely existing when using a hand-held camera especially under the dim lighting conditions. Since edge information contained in the noisy image may be blurred by the motion blur, a blurred/noisy image pair captured under different exposure time can help to restore a sharp image. In the traditional deblurring methods based on blurred/noisy image pair, the deblurring process is in series with the denoising process, so that restoration result is sensitive to the denoised result. In this paper, we propose a robust algorithm to obtain the sharp image by fusing the blurred image and noisy image. By joint modeling the deblurring model and denoising model, the restoration result can be optimized via estimating the sharp image and blur kernel alternately in the proposed methods, and it is not sensitive to the denoised result benefited by the joint model. Experimental results demonstrated that the proposed method can achieve better performance compared with the state-of-the-art single image denoising methods, single image deblurring methods and blurred/noisy pair deblurring methods.

show abstract

Motion deblurring using edge map with blurred/noisy image pairs

Cited by 15 publications

References 13 publications

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Near-Infrared Coloring via a Contrast-Preserving Mapping Model

Image Restoration with Multiple Hard Constraints on Data-Fidelity to Blurred/Noisy Image Pair

Joint Motion Deblurring with Blurred/Noisy Image Pair

Contact Info

Product

Resources

About