RGB/NIR Data Set

Realistic test data is needed to evaluate and rank the performance and quality of de-hazing algorithms for image enhancement. When it comes to professional photography and cinematography applications, this test data also has to fulfill specific quality standards, including high dynamic range, sufficient resolution and natural color reproduction.

To this end, we present a new multispectral data set that includes RGB and near-infrared (NIR) images captured by two professional digital motion picture cameras. Compared to existing data sets, the benefits of our set are threefold: Firstly, our two-camera approach means we are able to provide synchronous and well-registered RGB/NIR image pairs captured at the same instant of time. Secondly, high quality real image sequences allow future algorithms to take account of the temporal consistency of the de-hazed output images. And thirdly, to facilitate a uniform and fair evaluation of different algorithms we provide ground truth images for selected RGB/NIR image pairs.