View : 812 Download: 0
Learning Deeply Aggregated Alternating Minimization for General Inverse Problems
- Title
- Learning Deeply Aggregated Alternating Minimization for General Inverse Problems
- Authors
- Jung, Hyungjoo; Kim, Youngjung; Min, Dongbo; Jang, Hyunsung; Ha, Namkoo; Sohn, Kwanghoon
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2020
- Journal Title
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- ISSN
- 1057-7149
1941-0042
- Citation
- IEEE TRANSACTIONS ON IMAGE PROCESSING vol. 29, pp. 8012 - 8027
- Keywords
- Image restoration; Minimization; Noise reduction; Image resolution; Optimization; Training; Task analysis; Regularization-based image restoration; joint restoration; convolutional neural network; alternating minimization; half-quadratic minimization; proximal mapping
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- Regularization-based image restoration is one of the most powerful tools in image processing and computer vision thanks to its flexibility for handling various inverse problems. However, designing an optimal regularization function still remains unsolved since natural images and related scene types have a complex structure. In this paper, we present a general and principled framework, called deeply aggregated alternating minimization (DeepAM). We design a convolutional neural network (CNN) to implicitly parameterize the regularizer of the alternating minimization (AM) algorithm. Contrary to the conventional AM algorithm based on a point-wise proximal mapping, the DeepAM projects intermediate estimate into a set of natural images via deep aggregation. Since the CNN is fully integrated into the AM procedure, all parameters can be jointly optimized through end-to-end training. These properties enable the DeepAM to converge with a small number of iterations, while maintaining an algorithmic simplicity. We show that the DeepAM outperforms state-of-the-art methods, including nonlocal-based methods, Plug-and-Play regularization, and recent data-driven approaches. The effectiveness of our framework is demonstrated in a variety of image restoration tasks: Guassian denoising, deraining, deblurring, super-resolution, color-guided depth upsampling, and RGB/NIR restoration.
- DOI
- 10.1109/TIP.2020.3010082
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML