Ensemble learning priors unfolding for scalable Snapshot Compressive Sensing

TL;DR

This paper introduces an ensemble learning priors approach combined with scalable learning to enhance deep learning-based reconstruction in Snapshot Compressive Sensing, achieving state-of-the-art results on both simulated and real datasets.

Contribution

It proposes a novel ensemble learning priors method and scalable training framework to improve accuracy and generalizability of deep learning algorithms in SCI.

Findings

Achieved state-of-the-art reconstruction accuracy.

Demonstrated superior performance on real datasets.

Enhanced scalability of deep learning models for SCI.

Abstract

Snapshot compressive imaging (SCI) can record the 3D information by a 2D measurement and from this 2D measurement to reconstruct the original 3D information by reconstruction algorithm. As we can see, the reconstruction algorithm plays a vital role in SCI. Recently, deep learning algorithm show its outstanding ability, outperforming the traditional algorithm. Therefore, to improve deep learning algorithm reconstruction accuracy is an inevitable topic for SCI. Besides, deep learning algorithms are usually limited by scalability, and a well trained model in general can not be applied to new systems if lacking the new training process. To address these problems, we develop the ensemble learning priors to further improve the reconstruction accuracy and propose the scalable learning to empower deep learning the scalability just like the traditional algorithm. What's more, our algorithm has achieved the state-of-the-art results, outperforming existing algorithms. Extensive results on both simulation and real datasets demonstrate the superiority of our proposed algorithm. The code and models will be released to the public.