AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing

14 Oct 2020  ·  Nanyu Li, Charles C. Zhou ·

Compressed sensing (CS) is a challenging problem in image processing due to reconstructing an almost complete image from a limited measurement. To achieve fast and accurate CS reconstruction, we synthesize the advantages of two well-known methods (neural network and optimization algorithm) to propose a novel optimization inspired neural network which dubbed AMP-Net. AMP-Net realizes the fusion of the Approximate Message Passing (AMP) algorithm and neural network. All of its parameters are learned automatically. Furthermore, we propose an AMPA-Net which uses three attention networks to improve the representation ability of AMP-Net. Finally, We demonstrate the effectiveness of AMP-Net and AMPA-Net on four standard CS reconstruction benchmark data sets. Our code is available on

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Compressive Sensing BSD68 CS=50% AMPA-Net Average PSNR 36.33 # 1
Compressive Sensing BSDS100 - 2x upscaling AMPA-Net Average PSNR 35.95 # 1
Compressive Sensing Set11 cs=50% AMPA-Net Average PSNR 40.32 # 1
Compressive Sensing Urban100 - 2x upscaling AMPA-Net Average PSNR 35.86 # 1


No methods listed for this paper. Add relevant methods here