Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery

Abstract

Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands. In this paper we propose the Learning Synthesis by DNN (LS-DNN) approach where two DNNs process the low and high spatial frequencies, respectively, and, improving over [30], the two DNNs are trained separately and a third DNN combines them into an image with high fidelity at all bands. We demonstrate LS-DNN in two canonical inverse problems: super-resolution (SR) in diffraction-limited imaging (DLI), and quantitative phase retrieval (QPR). Our results also show comparable or improved performance over perceptual-loss based SR [21], and can be generalized to a wider range of image recovery problems.

arXiv comment10 pages, 10 figures. Supplement file can be provided upon reasonable request

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Understanding Neural Networks Through Deep Visualization
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Deep Learning Microscopy
• Low Photon Count Phase Retrieval Using Deep Learning
• Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery
• Spectral pre-modulation of training examples enhances the spatial resolution of the Phase Extraction Neural Network (PhENN)

Cited by in corpus (4)

• Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks
• Towards smart optical focusing: Deep learning-empowered wavefront shaping in nonstationary scattering media
• Low Photon Budget Phase Retrieval with Perceptual Loss Trained Deep Neural Networks