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 dataset consists of 50 high resolution image pairs captured by dual-camera setup for single image defocus deblurring . Please note this is not a training set but a benchmark assessment.