6 datasets found

A dataset for egocentric human interaction in real-world settings.

A benchmark for real-world image super-resolution.

The dataset is used for evaluating the performance of fisheye image rectification algorithms. It contains real-world fisheye images with their corresponding ground truth images...

The Realworld Kitchen dataset contains four sub-tasks, namely, opening the oven, grasping a cloth, closing a drawer, and turning on a light.

The dataset used in this paper for testing the 3D-RecGAN++ model. It contains 1.5k SV and 2.5k CV testing datasets for each of the 6 categories.

A dataset used for testing the proposed DPENet, comprising 300 rainy images with varying rain streak orientations and magnitudes.