信号处理2025，Vol.41Issue(4)：583-594,12.DOI:10.12466/xhcl.2025.04.001
视差引导的可变形卷积光场图像超分辨重建方法
Disparity-Guided Deformable Convolution for Light Field Image Super-Resolution
摘要
Abstract
Light field image super-resolution reconstruction aims to enhance the resolution of light field images by utiliz-ing complementary information across different views.This process focuses on restoring image details and improving overall image quality.The primary devices for capturing light field images are microlens cameras(such as Lytro and RayTrix cameras)and camera arrays.In microlens cameras,the maximum disparity between the images recorded from different viewpoints is typically less than one pixel.In contrast,for camera arrays,this maximum disparity can exceed one pixel.Most existing super-resolution reconstruction methods for light field images are tailored for microlens cam-eras;however,when applied to large disparity images(e.g.,those captured by array cameras),these methods often ex-perience significant performance degradation due to inadequate utilization of complementary information among differ-ent views.Inspired by light field disparity estimation techniques and deformable convolutional networks,this paper pres-ents a disparity-guided deformable convolution method for light field image super-resolution.This method captures complementary information in the view domain of light field images with large disparities.The proposed approach be-gins by estimating the disparity of each sub-view image within the light field.It then generates deformable convolution offsets based on the disparity map,facilitating inter-view feature alignment and the combination of complementary infor-mation.Ultimately,the method achieves feature fusion and super-resolution reconstruction through a multi-level distilla-tion mechanism.The effectiveness of the algorithm is validated on five widely used public light field datasets.Experi-mental results demonstrate that the proposed method achieves state-of-the-art performance in super-resolution reconstruc-tion and is robust against large disparities.关键词
光场/超分辨/视差估计/可变形卷积Key words
light field/super-resolution/disparity estimation/deformable convolution分类
信息技术与安全科学引用本文复制引用
杨俊刚,王应谦,梁政宇,吴天昊,安玮..视差引导的可变形卷积光场图像超分辨重建方法[J].信号处理,2025,41(4):583-594,12.基金项目
国家自然科学基金创新研究群体(61921001) （61921001）
国家自然科学基金青年基金(62401590) （62401590）
湖南省自然科学基金杰出青年基金(2024JJ2063)The National Natural Science Foundation of China(61921001,62401590) （2024JJ2063）
Distinguished Young Scholar Natural Science Foundation of Hunan Province,China(2024JJ2063) （2024JJ2063）
