Abstract
We propose a motion deblurring algorithm that exploits sparsity constraints of image patches using one single frame. In our formulation, each image patch is encoded with sparse coefficients using an over-complete dictionary. The sparsity constraints facilitate recovering the latent image without solving an ill-posed deconvolution problem. In addition, the dictionary is learned and updated directly from one single frame without using additional images. The proposed method iteratively utilizes sparsity constraints to recover latent image, estimates the deblur kernel, and updates the dictionary directly from one single image. The final deblurred image is then recovered once the deblur kernel is estimated using our method. Experiments show that the proposed algorithm achieves favorable results against the state-of-the-art methods.
| Original language | English |
|---|---|
| Title of host publication | 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings |
| Pages | 1169-1172 |
| Number of pages | 4 |
| DOIs | |
| Publication status | Published - 2010 Dec 1 |
| Event | 2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong Duration: 2010 Sep 26 → 2010 Sep 29 |
Publication series
| Name | Proceedings - International Conference on Image Processing, ICIP |
|---|---|
| ISSN (Print) | 1522-4880 |
Other
| Other | 2010 17th IEEE International Conference on Image Processing, ICIP 2010 |
|---|---|
| Country | Hong Kong |
| City | Hong Kong |
| Period | 10/9/26 → 10/9/29 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
}
Single image deblurring with adaptive dictionary learning. / Hu, Zhe; Huang, Jia Bin; Yang, Ming Hsuan.
2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 1169-1172 5651892 (Proceedings - International Conference on Image Processing, ICIP).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Single image deblurring with adaptive dictionary learning
AU - Hu, Zhe
AU - Huang, Jia Bin
AU - Yang, Ming Hsuan
PY - 2010/12/1
Y1 - 2010/12/1
N2 - We propose a motion deblurring algorithm that exploits sparsity constraints of image patches using one single frame. In our formulation, each image patch is encoded with sparse coefficients using an over-complete dictionary. The sparsity constraints facilitate recovering the latent image without solving an ill-posed deconvolution problem. In addition, the dictionary is learned and updated directly from one single frame without using additional images. The proposed method iteratively utilizes sparsity constraints to recover latent image, estimates the deblur kernel, and updates the dictionary directly from one single image. The final deblurred image is then recovered once the deblur kernel is estimated using our method. Experiments show that the proposed algorithm achieves favorable results against the state-of-the-art methods.
AB - We propose a motion deblurring algorithm that exploits sparsity constraints of image patches using one single frame. In our formulation, each image patch is encoded with sparse coefficients using an over-complete dictionary. The sparsity constraints facilitate recovering the latent image without solving an ill-posed deconvolution problem. In addition, the dictionary is learned and updated directly from one single frame without using additional images. The proposed method iteratively utilizes sparsity constraints to recover latent image, estimates the deblur kernel, and updates the dictionary directly from one single image. The final deblurred image is then recovered once the deblur kernel is estimated using our method. Experiments show that the proposed algorithm achieves favorable results against the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=78651106513&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78651106513&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2010.5651892
DO - 10.1109/ICIP.2010.5651892
M3 - Conference contribution
AN - SCOPUS:78651106513
SN - 9781424479948
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1169
EP - 1172
BT - 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
ER -