KIT | KIT-Bibliothek | Impressum | Datenschutz

A Multispectral Light Field Dataset for Light Field Deep Learning

Schambach, Maximilian; Heizmann, Michael

Abstract:
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 data\-set, 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.

Open Access Logo


Download
Originalveröffentlichung
DOI: 10.21227/y90t-xk47
Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Forschungsdaten
Publikationsmonat/-jahr 10.2020
Identifikator KITopen-ID: 1000125599
Relationen in KITopen
URL https://ieee-dataport.org/open-access/multispectral-light-field-dataset-light-field-deep-learning
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page