Laser & Optoelectronics Progress, Volume. 61, Issue 4, 0411007(2024)
Self-Supervised Learning for Spatial-Domain Light-Field Super-Resolution Imaging
This paper proposes a self-supervised learning-based method for the super-resolution imaging of spatial-domain resolution-limited light-field images. Using deep learning self-encoding, a super-resolution reconstruction of the spatial-domain is performed simultaneously for all light field sub-aperture images. A hybrid loss function based on multi-scale feature structure and total variation regularization is designed to constrain the similarity of the model output image to the original low-resolution image. Numerical experiments show that the newly proposed method has a suppressive effect on noise, and the resultant average super-resolutions for different light field imaging datasets exceed those of the supervised learning-based method for light field spatial domain images.
Get Citation
Copy Citation Text
Dan Liang, Haimiao Zhang, Jun Qiu. Self-Supervised Learning for Spatial-Domain Light-Field Super-Resolution Imaging[J]. Laser & Optoelectronics Progress, 2024, 61(4): 0411007
Category: Imaging Systems
Received: Apr. 27, 2023
Accepted: Jun. 28, 2023
Published Online: Feb. 22, 2024
The Author Email: Qiu Jun (qiujun@bistu.edu.cn)