Corpus ID: 239768679

Dynamic Proximal Unrolling Network for Compressive Imaging

@inproceedings{Yang2021DynamicPU,
  title={Dynamic Proximal Unrolling Network for Compressive Imaging},
  author={Yixiao Yang and Ran Tao and Kaixuan Wei and Ying Fu},
  year={2021}
}
  • Yixiao Yang, Ran Tao, +1 author Ying Fu
  • Published 2021
  • Engineering, Computer Science
Compressive imaging aims to recover a latent image from under-sampled measurements, suffering from a serious illposed inverse problem. Recently, deep neural networks have been applied to this problem with superior results, owing to the learned advanced image priors. These approaches, however, require training separate models for different imaging modalities and sampling ratios, leading to overfitting to specific settings. In this paper, a dynamic proximal unrolling network (dubbed DPUNet) was… Expand