用无监督学习重建水面形貌，还原水下图像
Looking Into the Water by Unsupervised Learning of the Surface Shape
- 双神经场模型分别预测水面高度和图像颜色
- 在模拟与真实数据上均优于现有无监督恢复方法
- 可同时估计水面形貌，适合遥感与视频修复场景
本文解决从空中观察水体时因水面折射导致的图像失真问题。假设水下图像恒定，提出由两个神经场网络组成的模型：第一个网络预测任意空间位置和时间的水面高度，第二个网络预测对应位置的图像颜色。通过联合重建观测到的图像序列，实现无监督训练。实验表明，使用带有周期性激活函数（SIREN）的隐式神经表示能有效建模水面高度及其梯度，满足图像重建需求。在模拟与真实数据上，本方法均优于最新无监督图像恢复方法，并可提供水面形貌估计。
原文摘要 · Abstract (English)
We address the problem of looking into the water from the air, where we seek to remove image distortions caused by refractions at the water surface. Our approach is based on modeling the different water surface structures at various points in time, assuming the underlying image is constant. To this end, we propose a model that consists of two neural-field networks. The first network predicts the height of the water surface at each spatial position and time, and the second network predicts the image color at each position. Using both networks, we reconstruct the observed sequence of images and can therefore use unsupervised training. We show that using implicit neural representations with periodic activation functions (SIREN) leads to effective modeling of the surface height spatio-temporal signal and its derivative, as required for image reconstruction. Using both simulated and real data we show that our method outperforms the latest unsupervised image restoration approach. In addition, it provides an estimate of the water surface.
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。