电子学报2024，Vol.52Issue(12)：4113-4124,12.DOI:10.12263/DZXB.20240253
基于穿插特征更新的光场图像超分网络
Cross Feature Updating-Based Network for Light Field Image Super Resolution
摘要
Abstract
Addressing the issue of low spatial resolution in light field image,cross feature updating-based network for light field image super resolution is built in this paper to generate a higher quality array of light field sub-aperture imag-es.In this work,a 3-branch structure is adopted for shallow feature extraction.In order to extract spatial and angular fea-tures from different forms of light field data,parallel residual block is designed.A cross feature update structure is used for extract deep features,and feature alignment interaction module,self-attention feature interaction module,and spatial feature enhancement module are designed to achieve step-by-step fusion and updating of spatial and angular features.In the data re-construction part,the updated spatial information is fused by using multi-scale residual block and channel attention block al-ternately and finally super-resolution images are obtained through data upsampling.On the basis of fully exploring and sup-plementing spatial and angular features,the proposed network adopts a step-by-step fusion,update,and enhancement mech-anism to gather spatial information at different levels,leading to superior super-resolution results.Comparative experiments demonstrate the effectiveness of the proposed method,with the network achieving an average peak signal-to-noise ratio(PSNR)value of 32.31 dB for 4×tasks on 5 public light field datasets,surpassing the performance of existing networks.关键词
4D光场/超分辨率重建/穿插特征更新/特征对齐交互/自注意力特征交互Key words
4D light field/super-resolution reconstruction/cross feature updating/feature alignment interaction/self-attention feature interaction分类
信息技术与安全科学引用本文复制引用
陈佳妮,武迎春,吕天琪,刘丽,赵贤凌..基于穿插特征更新的光场图像超分网络[J].电子学报,2024,52(12):4113-4124,12.基金项目
国家自然科学基金(No.61601318) （No.61601318）
山西省自然科学基金(No.202103021224278) （No.202103021224278）
山西省回国留学人员科研项目(No.2020-128) National Natural Science Foundation of China(No.61601318) （No.2020-128）
Natural Science Foundation of Shanxi Province(No.202103021224278) （No.202103021224278）
Research Project Supported by Shanxi Scholarship Council of China(No.2020-128) （No.2020-128）
