用神经网络消除大气湍流造成的图像模糊，验证现有模型的适用性。
Evaluation of neural network algorithms for atmospheric turbulence mitigation
- 测试五种神经网络架构，端到端训练无需预稳定步骤。
- 验证现有模型在大气湍流去模糊任务中的可复用性。
- 为专用于湍流抑制的系统设计提供架构参考。
多种神经网络架构正被研究用于解决因非稳态相机和被摄物体运动导致的图像与视频模糊问题。本文综述了现有网络，并通过实验评估其在消除大气湍流引起的模糊方面的效果。实验旨在检验现有网络在该任务中的可复用性，并识别出适用于专门针对大气湍流抑制系统的理想架构特征。我们对比了五种不同架构，其中包括一个采用端到端训练的网络，从而无需预先稳定步骤。
原文摘要 · Abstract (English)
A variety of neural networks architectures are being studied to tackle blur in images and videos caused by a non-steady camera and objects being captured. In this paper, we present an overview of these existing networks and perform experiments to remove the blur caused by atmospheric turbulence. Our experiments aim to examine the reusability of existing networks and identify desirable aspects of the architecture in a system that is geared specifically towards atmospheric turbulence mitigation. We compare five different architectures, including a network trained in an end-to-end fashion, thereby removing the need for a stabilization step.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。