Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging
This work addresses the need for fast and accurate SCI recovery algorithms, which is incremental as it builds on existing deep unfolding networks by incorporating novel modules.
The paper tackles the problem of snapshot compressive imaging (SCI) recovery by proposing a dense deep unfolding network with a 3D-CNN prior and dense feature map strategy to improve spatial-temporal correlation and reduce information loss, achieving superior performance in experiments on simulation and real data.
Snapshot compressive imaging (SCI) aims to record three-dimensional signals via a two-dimensional camera. For the sake of building a fast and accurate SCI recovery algorithm, we incorporate the interpretability of model-based methods and the speed of learning-based ones and present a novel dense deep unfolding network (DUN) with 3D-CNN prior for SCI, where each phase is unrolled from an iteration of Half-Quadratic Splitting (HQS). To better exploit the spatial-temporal correlation among frames and address the problem of information loss between adjacent phases in existing DUNs, we propose to adopt the 3D-CNN prior in our proximal mapping module and develop a novel dense feature map (DFM) strategy, respectively. Besides, in order to promote network robustness, we further propose a dense feature map adaption (DFMA) module to allow inter-phase information to fuse adaptively. All the parameters are learned in an end-to-end fashion. Extensive experiments on simulation data and real data verify the superiority of our method. The source code is available at https://github.com/jianzhangcs/SCI3D.