Some tasks are inferred based on the benchmarks list.
The benchmarks section lists all benchmarks using a given dataset or any of
its variants. We use variants to distinguish between results evaluated on
slightly different versions of the same dataset. For example, ImageNet 32⨉32
and ImageNet 64⨉64 are variants of the ImageNet dataset.
This is a 4D light-field dataset of materials. The dataset contains 12 material categories, each with 100 images taken with a Lytro Illum, from which we extract about 30,000 patches in total.