Robust destriping method based on data-driven learning

doi:10.1016/j.infrared.2018.09.015

Robust destriping method based on data-driven learning

2018-11-01

12

PRE

AI

DOI：10.1016/j.infrared.2018.09.015

Original

Original request for help

Save

Abstract

En 中文

Destriping is the crucial first step of many multidetector imaging pipelines since the stripes greatly decrease the quality of obtained data and limit subsequent applications. It is also a severely ill-posed issue that estimates true gray value per pixel from a single stripe measurement. Existing approaches leverage hand-crafted filters or priors but show visually unsatisfactory results where some residual stripes still remain and the quantitative values of image data are lost. To address these problems, we propose a new data-driven method. We train a convolutional neural network on a large set of ground truth data instead of using hand-tuned filters. A UNet-like network is used to learn the regularity of complex stripe noise characteristics. To generate high-quality images, we combine a per-pixel loss and a perceptual loss to penalize mismatch between the network output and ground-truth images. Experiments show that our network significantly outperforms state-of-the-art destriping approaches in real-captured noise images of many imaging fields. Our code is available online at https://github.com/Kuangxd/DDL-SR.

Keywords:

Image destriping

Data-driven learning

Convolutional neural networks

Robust destriping method based on data-driven learning

Abstract

AI Summary

Journal

Organization