基于深度学习的光场超分辨率算法综述
Review of Light Field Super-Resolution Algorithm Based on Deep Learning
熊娅维 1王安志 1张凯丽1
作者信息
- 1. 贵州师范大学大数据与计算机科学学院,贵州 贵阳 550025
- 折叠
摘要
光场图像分辨率低的原因之一是光场空间分辨率和角度分辨率之间存在相互制约.光场超分辨率技术旨在从低分辨率光场图像中重建出高分辨率光场图像.基于深度学习的光场超分辨率方法通过学习高、低分辨率光场图像之间的映射关系来提升图像的质量,突破了传统方法计算成本高、操作复杂的限制.本文对近年来基于深度学习的光场超分辨率技术研究进展进行了全面综述,梳理了网络框架和典型算法,并进行了实验对比分析.最后,总结了光场超分辨率领域面临的挑战,并展望了未来可能的发展方向.
Abstract
The trade-off between spatial and angular resolutions is one of the reasons for low-resolution light field images.Light field super-resolution techniques aim to reconstruct high-resolution light field images from low-resolution light field images.Deep learning-based light field super-resolution methods improve the quality of images by learning the mapping relationship between high-and low-resolution light field images.This advantage breaks through the limitations of traditional methods with high computational cost and complex operation.This paper provides a comprehensive overview of the research progress of deep learning-based light field super-resolution technology in recent years.The network framework and typical algorithms are examined,and experimental comparative analysis is conducted.Furthermore,the challenges faced in the area of light field super-resolution are summarized,and the future development direction is anticipated.
关键词
光场/图像超分辨/图像修复/深度学习Key words
light field/image super-resolution/image inpainting/deep learning引用本文复制引用
基金项目
国家自然科学基金地区科学基金项目(62162013)
贵州师范大学学术新苗基金项目(黔师新苗[2022]30号)
出版年
2024
NETL
NSTL
万方数据