Abstract
This paper addresses the single-image compressive sensing (CS) and reconstruction problem. We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction. LAPRAN progressively reconstructs an image following the concept of Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods. Experimental results on multiple public datasets show that LAPRAN offers an average 7.47dB and 5.98dB PSNR, and an average 57.93% and 33.20% SSIM improvement compared to model-based and data-driven baselines, respectively.
Abstract (translated)
本文讨论了单图像压缩感知（CS）和重建问题。我们提出了一种可扩展的拉普拉斯金字塔重建对抗网络（LAPRAN），可实现高保真，灵活和快速的CS图像重建。 LAPRAN通过重建对抗性网络（RAN）的多个阶段逐步重建遵循拉普拉斯金字塔概念的图像。在每个金字塔等级，CS测量值与上下文潜在向量融合以生成高频图像残差。因此，LAPRAN可以生成重建图像的层次结构，并且每个都具有增量分辨率和改进的质量。 LAPRAN的可扩展金字塔结构可实现高保真CS重建，灵活的分辨率适用于各种压缩比（CR），这在现有方法中是不可行的。多个公共数据集的实验结果表明，与基于模型和数据驱动的基线相比，LAPRAN分别提供平均7.47dB和5.98dB PSNR，平均57.79％和33.20％SSIM改善。
URL
https://arxiv.org/abs/1807.09388
