Phase Retrieval using Single-Instance Deep Generative Prior

06/09/2021

∙

Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.

READ FULL TEXT

Phase Retrieval using Single-Instance Deep Generative Prior

Practical Phase Retrieval Using Double Deep Image Priors

Self-Validation: Early Stopping for Single-Instance Deep Generative Priors

GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image

DOLPH: Diffusion Models for Phase Retrieval

DeepInit Phase Retrieval

A Deep Generative Approach to Oversampling in Ptychography

Learning to Generate 3D Representations of Building Roofs Using Single-View Aerial Imagery

Phase Retrieval using Single-Instance Deep Generative Prior

Related Research

Practical Phase Retrieval Using Double Deep Image Priors

Self-Validation: Early Stopping for Single-Instance Deep Generative Priors

GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image

DOLPH: Diffusion Models for Phase Retrieval

DeepInit Phase Retrieval

A Deep Generative Approach to Oversampling in Ptychography

Learning to Generate 3D Representations of Building Roofs Using Single-View Aerial Imagery