LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
复制标题
DOI：
10.1007/978-3-030-01249-6_30
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Kai Xu;Zhikang Zhang;Fengbo Ren
中科院分区：
文献类型：
--
作者：
Kai Xu;Zhikang Zhang;Fengbo Ren
本文研究了单图像压缩感知（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），可以实现高保真，灵活和快速的CS图像重建。该算法遵循拉普拉斯金字塔的概念，通过重构对抗网络（RANs）的多个阶段逐步重建图像。在每个金字塔级别，CS测量与上下文潜在向量融合，以产生高频图像残差。因此，LAPRAN可以产生重建图像的层次，每个层次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，具有灵活的分辨率，可适应大范围的压缩比（CRs），这是现有方法无法实现的。在多个公共数据集上的实验结果表明，与基于模型和数据驱动的基线相比，LAPRAN的平均PSNR分别为7.47 dB和5.98 dB， SSIM分别为57.93%和33.20%。
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 the 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 7.47 dB and 5.98 dB PSNR, and an average 57.93% and 33.20% SSIM improvement compared to model-based and data-driven baselines, respectively.