Deep Unfolding-Aided Parameter Tuning for Plug-and-Play-Based Video Snapshot Compressive Imaging

TL;DR

This paper introduces a deep unfolding method to optimize noise level parameters in plug-and-play algorithms for video snapshot compressive imaging, improving reconstruction accuracy and providing new theoretical insights.

Contribution

It presents a novel deep unfolding approach for tuning noise parameters in PnP-based video SCI, with insights into their non-monotonic patterns and convergence behavior.

Findings

Deep unfolding effectively tunes noise parameters in PnP algorithms.

Trained parameters show non-monotonic patterns, challenging existing assumptions.

Provides new theoretical insights into PnP algorithm convergence.

Abstract

Snapshot compressive imaging (SCI) captures high-dimensional data efficiently by compressing it into two-dimensional observations and reconstructing high-dimensional data from two-dimensional observations with various algorithms. The plug-and-play (PnP) method is a promising approach for the video SCI reconstruction because it can leverage both observation models and denoising methods for videos. Since the reconstruction accuracy significantly depends on the choice of noise level parameters, this paper proposes a deep unfolding-based method for tuning these parameters in PnP-based video SCI. For the training of the parameters, we prepare training data from the densely annotated video segmentation dataset, reparametrize the noise level parameters, and apply the checkpointing technique to reduce the required memory. Simulation results show that the trained noise level parameters via the proposed approach exhibit a non-monotonic pattern, which is different from the assumptions in the conventional convergence analyses of PnP-based algorithms. These findings provide new insights into both the application of deep unfolding and the theoretical basis of PnP algorithms.