论文标题
4D光场视频的深度估算
Depth estimation from 4D light field videos
论文作者
论文摘要
在过去几年中，4D光场（LF）图像的深度（差异）估计一直是研究主题。大多数研究都集中在静态4D LF图像中的深度估计上，同时不考虑时间信息，即LF视频。本文提出了一个端到端的神经网络体系结构，以从4D LF视频中进行深度估算。这项研究还构建了一个中等规模的合成4D LF视频数据集，可用于培训基于深度学习的方法。使用合成和现实世界4D LF视频的实验结果表明，时间信息有助于提高嘈杂区域的深度估计准确性。数据集和代码可在以下网址获得：https：//mediaeng-lfv.github.io/lfv_disparity_estimation
Depth (disparity) estimation from 4D Light Field (LF) images has been a research topic for the last couple of years. Most studies have focused on depth estimation from static 4D LF images while not considering temporal information, i.e., LF videos. This paper proposes an end-to-end neural network architecture for depth estimation from 4D LF videos. This study also constructs a medium-scale synthetic 4D LF video dataset that can be used for training deep learning-based methods. Experimental results using synthetic and real-world 4D LF videos show that temporal information contributes to the improvement of depth estimation accuracy in noisy regions. Dataset and code is available at: https://mediaeng-lfv.github.io/LFV_Disparity_Estimation
