Geometry-aware light field angular super-resolution using multiple representations

Light Field Angular Super-Resolution (LFASR) is a critical task that enables applications such as depth estimation, refocusing, and 3D scene reconstruction. Acquiring LFASR from Plenoptic cameras has an inherent trade-off between the angular and spatial resolution due to sensor limitations. To addre...

Full description

Saved in:
Bibliographic Details
Main Author: Tariq Saeed Mian
Format: Article
Language:English
Published: Universitas Ahmad Dahlan 2025-08-01
Series:IJAIN (International Journal of Advances in Intelligent Informatics)
Subjects:
Online Access:https://ijain.org/index.php/IJAIN/article/view/1667
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Light Field Angular Super-Resolution (LFASR) is a critical task that enables applications such as depth estimation, refocusing, and 3D scene reconstruction. Acquiring LFASR from Plenoptic cameras has an inherent trade-off between the angular and spatial resolution due to sensor limitations. To address this challenge, many learning-based LFASR methods have been proposed; however, the reconstruction problem of LF with a wide baseline remains a significant challenge. In this study, we proposed an end-to-end learning-based geometry-aware network using multiple representations. A multi-scale residual network with varying receptive fields is employed to effectively extract spatial and angular features, enabling angular resolution enhancement without compromising spatial fidelity. Extensive experiments demonstrate that the proposed method effectively recovers fine details with high angular resolution while preserving the intricate parallax structure of the light field. Quantitative and qualitative evaluations on both synthetic and real-world datasets further confirm that the proposed approach outperforms existing state-of-the-art methods. This research improves the angular resolution of the light field without reducing spatial sharpness, supporting applications such as depth estimation and 3D reconstruction. The method is able to preserve parallax details and structure with better results than current methods.
ISSN:2442-6571
2548-3161