VALSE 论文速览 第180期：基于非局部空间-角度关联的光场图像超分辨 ...

论文题目：

Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution

作者列表：

梁政宇 (国防科技大学), 王应谦 (国防科技大学), 王龙光 (空军航空大学), 杨俊刚 (国防科技大学), 周石琳 (国防科技大学), 郭裕兰 (国防科技大学)

B站观看网址：

https://www.bilibili.com/video/BV1bw4m1q7Am/

论文摘要：

Exploiting spatial-angular correlation is crucial to light field (LF) image super-resolution (SR), but is highly challenging due to its non-local property caused by the disparities among LF images. Although many deep neural networks (DNNs) have been developed for LF image SR and achieved continuously improved performance, existing methods cannot well leverage the long-range spatial-angular correlation and thus suffer a significant performance drop when handling scenes with large disparity variations. In this paper, we propose a simple yet effective method to learn the non-local spatial-angular correlation for LF image SR. In our method, we adopt the epipolar plane image (EPI) representation to project the 4D spatial-angular correlation onto multiple 2D EPI planes, and then develop a Transformer network with repetitive self-attention operations to learn the spatial-angular correlation by modeling the dependencies between each pair of EPI pixels. Our method can fully incorporate the information from all angular views while achieving a global receptive field along the epipolar line. We conduct extensive experiments with insightful visualizations to validate the effectiveness of our method. Comparative results on five public datasets show that our method not only achieves state-of-the-art SR performance but also performs robust to disparity variations. Code is publicly available at https://github.com/ZhengyuLiang24/EPIT.

论文链接：

[https://arxiv.org/abs/2302.08058]

代码链接：

[https://github.com/ZhengyuLiang24/EPIT]

视频讲者简介：

梁政宇，国防科技大学博士生。主要研究内容为光学成像、底层视觉、光场图像处理。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：张瑞茂 (香港中文大学 (深圳))