Datasets
Open Access
A Multispectral Light Field Dataset for Light Field Deep Learning
- Citation Author(s):
- Submitted by:
- Maximilian Schambach
- Last updated:
- Tue, 05/17/2022 - 22:21
- DOI:
- 10.21227/y90t-xk47
- Link to Paper:
- Links:
- License:
- Categories:
- Keywords:
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.
Dataset Files
- DATASET_MULTISPECTRAL_RAW.zip (1,004.92 GB)
- DATASET_MULTISPECTRAL_PATCHED_F_11x11_36x36.zip (372.60 GB)
- DATASET_MULTISPECTRAL_PATCHED_F_9x9_36x36.zip (249.58 GB)
- DATASET_MULTISPECTRAL_PATCHED_INF_9x9_36x36.zip (249.58 GB)
- DATASET_RGB_PATCHED_F_9x9_36x36.zip (57.96 GB)
- DATASET_RGB_PATCHED_INF_9x9_36x36.zip (57.96 GB)
- CHALLENGES_MULTISPECTRAL.zip (72.37 GB)
- CHALLENGES_RGB.zip (15.03 GB)
- SCRIPTS.zip (16.33 kB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.