# Invertible generative models for inverse problems: mitigating representation error and dataset bias

@article{Asim2019InvertibleGM, title={Invertible generative models for inverse problems: mitigating representation error and dataset bias}, author={Muhammad Asim and Ali Ahmed and Paul Hand}, journal={ArXiv}, year={2019}, volume={abs/1905.11672} }

Trained generative models have shown remarkable performance as priors for inverse problems in imaging. For example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any particular image because of architectural choices, mode collapse, and bias in the training dataset. In this paper, we demonstrate that invertible neural networks, which have zero representation error by… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

#### Citations

##### Publications citing this paper.

SHOWING 1-6 OF 6 CITATIONS

## Compressed Sensing with Invertible Generative Models and Dependent Noise

VIEW 12 EXCERPTS

CITES BACKGROUND, METHODS & RESULTS

HIGHLY INFLUENCED

## Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior

VIEW 1 EXCERPT

CITES METHODS

## Reducing the Representation Error of GAN Image Priors Using the Deep Decoder

VIEW 1 EXCERPT

CITES METHODS

## Subsampled Fourier Ptychography via Pretrained Invertible and Untrained Network Priors

VIEW 1 EXCERPT

CITES METHODS

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 24 REFERENCES

## Glow: Generative Flow with Invertible 1x1 Convolutions

VIEW 10 EXCERPTS

HIGHLY INFLUENTIAL

## Compressed Sensing using Generative Models

VIEW 5 EXCERPTS

HIGHLY INFLUENTIAL

## Automated Flower Classification over a Large Number of Classes

VIEW 6 EXCERPTS

HIGHLY INFLUENTIAL

## The Caltech-UCSD Birds-200-2011 Dataset

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## Latent Convolutional Models

VIEW 1 EXCERPT

## Blind Image Deconvolution using Deep Generative Priors.

VIEW 2 EXCERPTS