A Multispectral Light Field Dataset and Framework for Light Field Deep Learning

• Main Authors: Maximilian Schambach, Michael Heizmann
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Dataset; deep learning; disparity; light field imaging; multispectral imaging
• Online Access: https://ieeexplore.ieee.org/document/9235496/

Deep learning undoubtedly has had a huge impact on the computer vision community in recent years. In light field imaging, machine learning-based applications have significantly outperformed their conventional counterparts. Furthermore, multi- and hyperspectral light fields have shown promising results in light field-related applications such as disparity or shape estimation. Yet, a multispectral light field dataset, enabling data-driven approaches, is missing. Therefore, we propose a new synthetic multispectral light field dataset with depth and disparity ground truth. The dataset consists of a training, validation and test dataset, containing light fields of randomly generated scenes, as well as a challenge dataset rendered from hand-crafted scenes enabling detailed performance assessment. Additionally, we present a Python framework for light field deep learning. The goal of this framework is to ensure reproducibility of light field deep learning research and to provide a unified platform to accelerate the development of new architectures. The dataset is made available under dx.doi.org/10.21227/y90t-xk47. The framework is maintained at gitlab.com/iiit-public/lfcnn.