Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 31, Issue -, Pages 216-226Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3127850
Keywords
Image restoration; Estimation; Task analysis; Training; Cameras; Image edge detection; Deep learning; Defocus; deblurring; anxiliary learning; CNNs
Funding
- National Natural Science Foundation of China [61771276]
- National Key Research and Development Program of China [2016YFB0101001]
Ask authors/readers for more resources
This paper proposes a network architecture called DID-ANet for single image defocus deblurring by using defocus map estimation as an auxiliary task. A large-scale dataset is also built for network training.
Different from the object motion blur, the defocus blur is caused by the limitation of the cameras' depth of field. The defocus amount can be characterized by the parameter of point spread function and thus forms a defocus map. In this paper, we propose a new network architecture called Defocus Image Deblurring Auxiliary Learning Net (DID-ANet), which is specifically designed for single image defocus deblurring by using defocus map estimation as auxiliary task to improve the deblurring result. To facilitate the training of the network, we build a novel and large-scale dataset for single image defocus deblurring, which contains the defocus images, the defocus maps and the all-sharp images. To the best of our knowledge, the new dataset is the first large-scale defocus deblurring dataset for training deep networks. Moreover, the experimental results demonstrate that the proposed DID-ANet outperforms the state-of-the-art methods for both tasks of defocus image deblurring and defocus map estimation, both quantitatively and qualitatively. The dataset, code, and model is available on GitHub: https://github.com/xytmhy/DID-ANet-Defocus-Deblurring.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available