TR2021-046
A Consensus Equilibrium Solution for Deep Image Prior Powered by Red
-
- "A Consensus Equilibrium Solution for Deep Image Prior Powered by Red", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP39728.2021.9414290, June 2021, pp. 1380-1384.BibTeX TR2021-046 PDF
- @inproceedings{Hyder2021jun,
- author = {{Hyder, Rakib and Mansour, Hassan and Ma, Yanting and Boufounos, Petros T. and Wang, Pu}},
- title = {A Consensus Equilibrium Solution for Deep Image Prior Powered by Red},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2021,
- pages = {1380--1384},
- month = jun,
- doi = {10.1109/ICASSP39728.2021.9414290},
- issn = {2379-190X},
- isbn = {978-1-7281-7605-5},
- url = {https://www.merl.com/publications/TR2021-046}
- }
,
- "A Consensus Equilibrium Solution for Deep Image Prior Powered by Red", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP39728.2021.9414290, June 2021, pp. 1380-1384.
-
MERL Contacts:
-
Research Areas:
Computational Sensing, Machine Learning, Optimization, Signal Processing
Abstract:
Recent advances in solving imaging inverse problems have witnessed the combination of deep learning models with classical image models for better signal representation. One such approach, DeepRED, combines the deep image prior (DIP) with the regularization by denoising (RED) framework to boost the performance of image deblurring and super resolution tasks. In this paper, we formulate DeepRED as a consensus equilibrium problem and set up a fixed-point algorithm for solving the equilibrium equations. We also derive sufficient conditions that the DIP generative prior should satisfy to ensure that the corresponding fixed-point operator is nonexpansive. We then demonstrate that the fixed-point algorithm that solves the CE equations results in improved image reconstruction quality in a deblurring setting compared to state-of-the-art methods