Deep Ptych: Subsampled Fourier Ptychography using Generative Priors

Shamshad, Fahad; Abbas, Farwa; Ahmed, Ali

doi:10.48550/arxiv.1812.11065

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generative priors have recently been employed in solving inverse problems such as compressed sensing [34], [35], phase retrieval [36], [37], Fourier ptychography [38], and image inpainting [39], etc. We also note work of [40] and [41] that use pretrained generators for circumventing the issue of adversarial attacks.…”

Section: Related Workmentioning

confidence: 99%

Blind Image Deconvolution using Deep Generative Priors

Asim¹,

Shamshad²,

Ahmed³

2018

Preprint

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel approach to regularize the ill-posed and non-linear blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate generative models -one trained to produce sharp images while the other trained to generate blur kernels from lower-dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show promising deblurring results on images even under large blurs, and heavy noise. To address the shortcomings of generative models such as mode collapse, we augment our generative priors with classical image priors and report improved performance on complex image datasets. The deblurring performance depends on how well the range of the generator spans the image class. Interestingly, our experiments show that even an untrained structured (convolutional) generative networks acts as an image prior in the image deblurring context allowing us to extend our results to more diverse natural image datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Blind Image Deconvolution using Deep Generative Priors

Asim¹,

Shamshad²,

Ahmed³

2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These methods show competitive performance, but since these generative model based approaches are end-to-end they suffer from the same draw backs as other deep learning based debluring approaches. On the other hand, pretrained generative models have recently been employed as regularizers to solve inverse problems in imaging including compressed sensing [2,30], image inpainting [37], Fourier ptychography [32], and phase retrieval [12,31]. However the applicability of these pretrained generative models in blind image deblurring is relatively unexplored.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Blind Image Deconvolution using Pretrained Generative Priors

Asim,

Shamshad,

Ahmed

2019

Preprint

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate deep generative models -one trained to produce sharp images while the other trained to generate blur kernels from lower-dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show excellent deblurring results even under large blurs and heavy noise. To improve the performance on rich image datasets not well learned by the generative networks, we present a modification of the proposed scheme that governs the deblurring process under both generative and classical priors.

show abstract

Deep Ptych: Subsampled Fourier Ptychography using Generative Priors

Cited by 2 publications

References 0 publications

Blind Image Deconvolution using Deep Generative Priors

Blind Image Deconvolution using Deep Generative Priors

Blind Image Deconvolution using Pretrained Generative Priors

Contact Info

Product

Resources

About