当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning from EPI-Volume-Stack for Light Field image angular super-resolution
Signal Processing: Image Communication ( IF 3.5 ) Pub Date : 2021-06-12 , DOI: 10.1016/j.image.2021.116353
Deyang Liu , Qiang Wu , Yan Huang , Xinpeng Huang , Ping An

Light Field (LF) image angular super-resolution aims to synthesize a high angular resolution LF image from a low angular resolution one, and is drawing increased attention because of its wide applications. In order to reconstruct a high angular resolution LF image, many learning based LF image angular super-resolution methods have been proposed. However, most existing methods are based on LF Epipolar Plane Image or Epipolar Plane Image volume representation, which underuse the LF image structure. The LF view spatial correlation and neighboring LF views angular correlations which can reflect LF image structure are not fully explored, which reduces LF angular super-resolution quality. In order to alleviate this problem, this paper introduces an Epipolar Plane Image Volume Stack (EPI-VS) representation for LF angular super-resolution. The EPI-VS is constituted by arranging all LF views in a raster order, which benefits in exploring LF view spatial correlation and neighboring LF views angular correlations. Based on such representation, we further propose an LF angular super-resolution network. 3D convolutions are applied in the whole super-resolution network to better accommodate the input EPI-VS data and allow information propagation between two spatial and one directional dimensions of EPI-VS data. Extensive experiments on synthetic and real-world LF scenes demonstrate the effectiveness of the proposed network. Moreover, we also illustrate the superiority of our network by applying it in scene depth estimation task.



中文翻译:

从 EPI-Volume-Stack 学习光场图像角度超分辨率

光场 (LF) 图像角超分辨率旨在从低角分辨率图像合成高角分辨率 LF 图像,并因其广泛的应用而引起越来越多的关注。为了重建高角分辨率LF图像,已经提出了许多基于学习的LF图像角超分辨率方法。然而,大多数现有方法是基于LF Epipolar Plane Image或Epipolar Plane Image体积表示,它们没有充分利用LF图像结构。LF视角空间相关性和能够反映LF图像结构的相邻LF视角角度相关性没有得到充分探索,这降低了LF角度超分辨率质量。为了缓解这个问题,本文介绍了一种用于 LF 角度超分辨率的对极平面图像体积堆栈 (EPI-VS) 表示。EPI-VS 由按光栅顺序排列所有 LF 视图构成,这有利于探索 LF 视图空间相关性和相邻 LF 视图角度相关性。基于这种表示,我们进一步提出了一个LF角度超分辨率网络。3D 卷积应用于整个超分辨率网络,以更好地适应输入的 EPI-VS 数据,并允许 EPI-VS 数据的两个空间维度和一个方向维度之间的信息传播。对合成和现实世界低频场景的大量实验证明了所提出网络的有效性。此外,我们还通过将其应用于场景深度估计任务来说明我们网络的优越性。基于这种表示,我们进一步提出了一个LF角度超分辨率网络。3D 卷积应用于整个超分辨率网络,以更好地适应输入的 EPI-VS 数据,并允许 EPI-VS 数据的两个空间维度和一个方向维度之间的信息传播。对合成和现实世界低频场景的大量实验证明了所提出网络的有效性。此外,我们还通过将其应用于场景深度估计任务来说明我们网络的优越性。基于这种表示,我们进一步提出了一个LF角度超分辨率网络。3D 卷积应用于整个超分辨率网络,以更好地适应输入的 EPI-VS 数据,并允许 EPI-VS 数据的两个空间维度和一个方向维度之间的信息传播。对合成和现实世界低频场景的大量实验证明了所提出网络的有效性。此外,我们还通过将其应用于场景深度估计任务来说明我们网络的优越性。对合成和现实世界低频场景的大量实验证明了所提出网络的有效性。此外,我们还通过将其应用于场景深度估计任务来说明我们网络的优越性。对合成和现实世界低频场景的大量实验证明了所提出网络的有效性。此外,我们还通过将其应用于场景深度估计任务来说明我们网络的优越性。

更新日期:2021-06-17
down
wechat
bug