Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lao, Dong, Wang, Congli, Wong, Alex, Soatto, Stefano
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911930303643648
author Lao, Dong
Wang, Congli
Wong, Alex
Soatto, Stefano
author_facet Lao, Dong
Wang, Congli
Wong, Alex
Soatto, Stefano
contents We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically impossible to obtain, assumptions and biases have to be imposed to solve this inverse problem, and we choose to model them explicitly. Rather than initializing a latent irradiance ("template") by heuristics to estimate deformation, we select one of the images as a reference, and model the deformation in this image by the aggregation of the optical flow from it to other images, exploiting a prior imposed by Central Limit Theorem. Then with a novel flow inversion module, the model registers each image TO the template but WITHOUT the template, avoiding artifacts related to poor template initialization. To illustrate the robustness of the method, we simply (i) select the first frame as the reference and (ii) use the simplest optical flow to estimate the warpings, yet the improvement in registration is decisive in the final reconstruction, as we achieve state-of-the-art performance despite its simplicity. The method establishes a strong baseline that can be further improved by integrating it seamlessly into more sophisticated pipelines, or with domain-specific methods if so desired.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03662
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
Lao, Dong
Wang, Congli
Wong, Alex
Soatto, Stefano
Computer Vision and Pattern Recognition
We describe a method for recovering the irradiance underlying a collection of images corrupted by atmospheric turbulence. Since supervised data is often technically impossible to obtain, assumptions and biases have to be imposed to solve this inverse problem, and we choose to model them explicitly. Rather than initializing a latent irradiance ("template") by heuristics to estimate deformation, we select one of the images as a reference, and model the deformation in this image by the aggregation of the optical flow from it to other images, exploiting a prior imposed by Central Limit Theorem. Then with a novel flow inversion module, the model registers each image TO the template but WITHOUT the template, avoiding artifacts related to poor template initialization. To illustrate the robustness of the method, we simply (i) select the first frame as the reference and (ii) use the simplest optical flow to estimate the warpings, yet the improvement in registration is decisive in the final reconstruction, as we achieve state-of-the-art performance despite its simplicity. The method establishes a strong baseline that can be further improved by integrating it seamlessly into more sophisticated pipelines, or with domain-specific methods if so desired.
title Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.03662