A Closer Look at Reference Learning for Fourier Phase Retrieval

Last update: Oct 28, 2021

Related tags

Overview

A Closer Look at Reference Learning for Fourier Phase Retrieval

This repository contains code for our NeurIPS 2021 Workshop on Deep Learning and Inverse Problems paper.

|-- references
|   |-- gs
|   |   |-- non-oversampled
|   |   |   |-- u_cifar_gs.npy
|   |   |   |-- u_emnist_gs.npy
|   |   |   |-- u_fmnist_gs.npy
|   |   |   |-- u_mnist_gs.npy
|   |   |   `-- u_svhn_gs.npy
|   |   `-- oversampled
|   |       |-- u_cifar.npy
|   |       |-- u_emnist.npy
|   |       |-- u_fmnist.npy
|   |       |-- u_mnist.npy
|   |       `-- u_svhn.npy
|   |-- hyder
|   |   |-- non-oversampled
|   |   |   |-- u_cifar.npy
|   |   |   |-- u_emnist.npy
|   |   |   |-- u_fmnist.npy
|   |   |   |-- u_mnist.npy
|   |   |   `-- u_svhn.npy
|   |   `-- oversampled
|   |       |-- u_celeba.npy
|   |       |-- u_cifar.npy
|   |       |-- u_emnist.npy
|   |       |-- u_fmnist.npy
|   |       |-- u_mnist.npy
|   |       `-- u_svhn.npy
|   `-- random
|       |-- u_ours_noiseless.npy
|       |-- u_ours.npy
|       |-- u_random_binary.npy
|       `-- u_random.npy
|-- data.py
|-- phase-retrieval-with-reference.ipynb
|-- README.md
|-- unrolled-GS.ipynb
`-- util.py

Requirements

All experiments were conducted with the following package versions:

numpy==1.19.5
torch==1.9.0
torchvision==0.10.0
matplotlib==3.4.3
scikit-image==0.17.2

The reference images for the oversampled case dicussed in Hyder et al. [1] were obtained from the official repository.

References

[1] Rakib Hyder, Zikui Cai, and M Salman Asif. Solving phase retrieval with a learned reference. In European Conference on Computer Vision, pages 425–441. Springer, 2020.

A Closer Look at Reference Learning for Fourier Phase Retrieval

Related tags

Overview

A Closer Look at Reference Learning for Fourier Phase Retrieval

Contents

Requirements

References

Owner

Tobias Uelwer

Diverse Branch Block: Building a Convolution as an Inception-like Unit

FEDn is an open-source, modular and ML-framework agnostic framework for Federated Machine Learning

This repo is the official implementation of "L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization".

Semi-supervised Implicit Scene Completion from Sparse LiDAR

An Implementation of SiameseRPN with Feature Pyramid Networks

v objective diffusion inference code for JAX.

Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

This repo includes the supplementary of our paper "CEMENT: Incomplete Multi-View Weak-Label Learning with Long-Tailed Labels"

Bayesian Image Reconstruction using Deep Generative Models

[CVPR'21] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

This is an official implementation for "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"

SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022

PyTorch Personal Trainer: My framework for deep learning experiments

A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".

Evolving neural network parameters in JAX.

L-Verse: Bidirectional Generation Between Image and Text

OBBDetection: an oriented object detection toolbox modified from MMdetection

NeuPy is a Tensorflow based python library for prototyping and building neural networks