The EYEDIAP dataset was designed to train and evaluate gaze estimation algorithms from RGB and RGB-D data. It contains a diversity of participants, head poses, gaze targets and sensing conditions.
The lack of a common benchmark for the evaluation of the gaze estimation task from RGB and RGB-D data is a serious limitation for distinguishing the advantages and disadvantages of the many proposed algorithms found in the literature.
The EYEDIAP dataset intends to fill the need for a standard database for gaze estimation from remote RGB, and RGB-D (standard vision and depth), cameras. The recording methodology was designed such that we systematically include, and isolate, most of the variables which affect the remote gaze estimation algorithms:
- Head pose variations.
- Person variation.
- Changes in ambient and sensing condition.
- Types of target: screen or 3D object.
Some pre-defined benchmarks are provided to evaluate each one of these aspects in an independent manner, and the data was preprocessed to extract and provide complementary observations (e.g. head pose).
The full database description and the download can be found here: EYEDIAP