Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 2602-2611Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00262
Keywords
-
Ask authors/readers for more resources
This paper introduces a framework that integrates deep image priors (DIP) into a plug-and-play regime for self-supervised spectral SCI reconstruction, demonstrating the ability to achieve competitive results on synthetic and actual data without training.
We consider using untrained neural networks to solve the reconstruction problem of snapshot compressive imaging (SCI), which uses a two-dimensional (2D) detector to capture a high-dimensional (usually 3D) data-cube in a compressed manner. Various SCI systems have been built in recent years to capture data such as high-speed videos, hyperspectral images, and the state-of-the-art reconstruction is obtained by the deep neural networks. However, most of these networks are trained in an end-to-end manner by a large amount of corpus with sometimes simulated ground truth, measurement pairs. In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction. Extensive synthetic and real data results show that the proposed algorithm without training is capable of achieving competitive results to the training based networks. Furthermore, by integrating the proposed method with a pre-trained deep denoising prior, we have achieved state-of-the-art results. Our code is available at https://github.com/mengziyi64/CASSI-Self-Supervised.
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