Here you can download the dataset of light fields used in the paper "How Do People Edit Light Fields". This includes synthetic and captured light fields, and include their reconstructed depth and disparity maps, so they can be directly used in the light field editing interface available here. If you use this code, please reference the following paper:

"How Do People Edit Light Fields?"
Adrian Jarabo, Belen Masia, Adrien Bousseau, Fabio Pellacini and Diego Gutierrez
ACM Trans. Graph. 33, 4 (2014)
@article{Jarabo:SIG14, author = {Jarabo, Adrian and Masia, Belen and Bousseau, Adrien and Pellacini, Fabio and Gutierrez, Diego}, title = {How Do People Edit Light Fields?}, journal = {ACM Transactions on Graphics (SIGGRAPH 2014)}, volume = {33}, number = {4} year = {2014}, }

The captured datasets come from three different sources: four light fields come from the dataset captured by Kim et al., that can be found here. One additional light field is captured with the Raytrix camera, and its depth was reconstructed by the work of Wanner and Goldluecke, found here. If these light fields are used, please cite the sources appropriately.

"Scene reconstruction from high spatio-angular resolution light fields"
Changil Kim, Henning Zimmer Yael Pritch and Alexander Sorkine-Hornung and Markus Gross
ACM Trans. Graph. 32, 4 (2012)

"Globally consistent depth labeling of 4D light fields"
Sven Wanner and Bastian Goldluecke
IEEE Computer Vision and Pattern Recognition (2012)

The remaining light fields have been captured with a Lytro, and its depth has been reconstructed using the LytroSDK.

Downloads

License