论文标题
大规模快照压缩成像的插入式算法
Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
论文作者
论文摘要
快照压缩成像（SCI）旨在使用单个快照中使用2D传感器（检测器）捕获高维（通常为3D）图像。尽管在我们的日常生活中享受了低型带宽，低功率和低成本的优势，但在大规模问题（HD或UHD视频）中应用SCI仍然具有挑战性。瓶颈在于重建算法；它们要么太慢（迭代优化算法），要么对编码过程（基于深度学习的端到端网络）不灵活。在本文中，我们基于插件（PNP）框架开发了SCI快速，灵活的算法。除了广泛使用的PNP-ADMM方法外，我们还进一步提出了具有较低计算工作负载的PNP-GAP（广义交替投影）算法，并证明在SCI硬件约束下PNP-GAP的收敛性。通过使用深层的先验，我们首次表明PNP可以从快照2D测量中恢复UHD彩色视频（$ 3840 \ times 1644 \ times 48 $，PNSR以上的PNSR高于30db）。模拟和实际数据集的广泛结果验证了我们提出的算法的优势。该代码可在https://github.com/liuyang12/pnp-sci上找到。
Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot. Though enjoying the advantages of low-bandwidth, low-power and low-cost, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging. The bottleneck lies in the reconstruction algorithms; they are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the widely used PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload and prove the convergence of PnP-GAP under the SCI hardware constraints. By employing deep denoising priors, we first time show that PnP can recover a UHD color video ($3840\times 1644\times 48$ with PNSR above 30dB) from a snapshot 2D measurement. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. The code is available at https://github.com/liuyang12/PnP-SCI.
