Deep Equilibrium Models for Video Snapshot Compressive Imaging
This work addresses the challenge of accurate and stable video recovery for snapshot compressive imaging systems, offering a method that improves upon existing models with theoretical soundness.
The paper tackles the inverse problem of recovering high-dimensional video from compressed, noisy measurements in snapshot compressive imaging by proposing deep equilibrium models (DEQ) that fuse data-driven regularization with stable convergence, achieving effective and stable reconstruction across various datasets and real data.
The ability of snapshot compressive imaging (SCI) systems to efficiently capture high-dimensional (HD) data has led to an inverse problem, which consists of recovering the HD signal from the compressed and noisy measurement. While reconstruction algorithms grow fast to solve it with the recent advances of deep learning, the fundamental issue of accurate and stable recovery remains. To this end, we propose deep equilibrium models (DEQ) for video SCI, fusing data-driven regularization and stable convergence in a theoretically sound manner. Each equilibrium model implicitly learns a nonexpansive operator and analytically computes the fixed point, thus enabling unlimited iterative steps and infinite network depth with only a constant memory requirement in training and testing. Specifically, we demonstrate how DEQ can be applied to two existing models for video SCI reconstruction: recurrent neural networks (RNN) and Plug-and-Play (PnP) algorithms. On a variety of datasets and real data, both quantitative and qualitative evaluations of our results demonstrate the effectiveness and stability of our proposed method. The code and models are available at: https://github.com/IndigoPurple/DEQSCI .