Learning Point Spread Function Invertibility Assessment for Image Deconvolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gualdrón-Hurtado, Romario, Jacome, Roman, Urrea, Sergio, Arguello, Henry, Gonzalez, Luis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917902939062272
author Gualdrón-Hurtado, Romario
Jacome, Roman
Urrea, Sergio
Arguello, Henry
Gonzalez, Luis
author_facet Gualdrón-Hurtado, Romario
Jacome, Roman
Urrea, Sergio
Arguello, Henry
Gonzalez, Luis
contents Deep-learning (DL)-based image deconvolution (ID) has exhibited remarkable recovery performance, surpassing traditional linear methods. However, unlike traditional ID approaches that rely on analytical properties of the point spread function (PSF) to achieve high recovery performance - such as specific spectrum properties or small conditional numbers in the convolution matrix - DL techniques lack quantifiable metrics for evaluating PSF suitability for DL-assisted recovery. Aiming to enhance deconvolution quality, we propose a metric that employs a non-linear approach to learn the invertibility of an arbitrary PSF using a neural network by mapping it to a unit impulse. A lower discrepancy between the mapped PSF and a unit impulse indicates a higher likelihood of successful inversion by a DL network. Our findings reveal that this metric correlates with high recovery performance in DL and traditional methods, thereby serving as an effective regularizer in deconvolution tasks. This approach reduces the computational complexity over conventional condition number assessments and is a differentiable process. These useful properties allow its application in designing diffractive optical elements through end-to-end (E2E) optimization, achieving invertible PSFs, and outperforming the E2E baseline framework.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16343
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Point Spread Function Invertibility Assessment for Image Deconvolution
Gualdrón-Hurtado, Romario
Jacome, Roman
Urrea, Sergio
Arguello, Henry
Gonzalez, Luis
Image and Video Processing
Computer Vision and Pattern Recognition
68T10 (Pattern Recognition), 94A08 (Image Processing)
I.4.5
Deep-learning (DL)-based image deconvolution (ID) has exhibited remarkable recovery performance, surpassing traditional linear methods. However, unlike traditional ID approaches that rely on analytical properties of the point spread function (PSF) to achieve high recovery performance - such as specific spectrum properties or small conditional numbers in the convolution matrix - DL techniques lack quantifiable metrics for evaluating PSF suitability for DL-assisted recovery. Aiming to enhance deconvolution quality, we propose a metric that employs a non-linear approach to learn the invertibility of an arbitrary PSF using a neural network by mapping it to a unit impulse. A lower discrepancy between the mapped PSF and a unit impulse indicates a higher likelihood of successful inversion by a DL network. Our findings reveal that this metric correlates with high recovery performance in DL and traditional methods, thereby serving as an effective regularizer in deconvolution tasks. This approach reduces the computational complexity over conventional condition number assessments and is a differentiable process. These useful properties allow its application in designing diffractive optical elements through end-to-end (E2E) optimization, achieving invertible PSFs, and outperforming the E2E baseline framework.
title Learning Point Spread Function Invertibility Assessment for Image Deconvolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
68T10 (Pattern Recognition), 94A08 (Image Processing)
I.4.5
url https://arxiv.org/abs/2405.16343