awesome-unsupervised-imaging
Resources for solving imaging inverse problems using deep learning without ground truth
https://github.com/andrewwango/awesome-unsupervised-imaging
Last synced: 6 days ago
JSON representation
-
Overviews
- Tutorial: self-supervised learning for imaging
- Deep learning techniques for inverse problems in imaging
- Imaging with equivariant deep learning: from unrolled network design to fully unsupervised learning
- Tutorial: self-supervised learning for imaging
- Imaging with equivariant deep learning: from unrolled network design to fully unsupervised learning
-
Frameworks
-
Equivariant imaging
- Equivariant Imaging: Learning Beyond the Range Space
- Self-Supervised Learning for Image Super-Resolution and Deblurring
- Equivariance-based self-supervised learning for audio signal recovery from clipped measurements
- Equivariant Imaging: Learning Beyond the Range Space
- Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements
- Sensing Theorems for Unsupervised Learning in Linear Inverse Problems
- Perspective-Equivariance for Unsupervised Imaging with Camera Geometry
- Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Temporal Equivariance
- Self-supervised learning with Equivariant Imaging for MRI | DeepInverse
- Image transformations for Equivariant Imaging | DeepInverse
-
Multi-operator algorithms
- Unsupervised Learning From Incomplete Measurements for Inverse Problems
- Self-supervised learning with measurement splitting | DeepInverse
- Self-supervised MRI reconstruction with Artifact2Artifact | DeepInverse
- Self-supervised learning from incomplete measurements of multiple operators | DeepInverse
- An Unbiased Risk Estimator for Image Denoising in the Presence of Mixed Poisson-Gaussian Noise
- UNSURE: Unknown Noise level Stein's Unbiased Risk Estimator
- Generalized SURE for Exponential Families: Applications to Regularization
- Noise2Noise: Learning Image Restoration without Clean Data
- Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
- Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image Denoising
- Self-supervised denoising with the SURE loss | DeepInverse
- Self-supervised denoising with the UNSURE loss | DeepInverse
- Self-supervised denoising with the Neighbor2Neighbor loss | DeepInverse
-
Generative models
- AmbientGAN: Generative models from lossy measurements
- Unsupervised Adversarial Image Reconstruction
- Progressive dual-domain-transfer cycleGAN for unsupervised MRI reconstruction
- Ambient Diffusion: Learning Clean Distributions from Corrupted Data
- GSURE-Based Diffusion Model Training with Corrupted Data
- Imaging inverse problems with adversarial networks | DeepInverse
- CoIL paper
- Kamilov 2022 DMBA Overview
-
-
Metrics
-
Generative models
-
-
Foundations
Categories