PhotIQA: A photoacoustic image data set with image quality ratings

To support the development and testing of full- and no-reference IQA measures we assembled PhotIQA, a data set consisting of 1134 photoacoustic (PA) images reconstructed with 3 different algorithms and ratings by 5 experts across five quality properties (overall quality, edge visibility, homogeneity, inclusion and background intensity). To allow full-reference assessment, highly characterised imaging test objects were used, providing a ground truth. A detailed description of the data set can be found in [1], where also baseline experiments give first insights. We have decided to make the data set available to the research community under the Creative Commons Attribution 4.0 International license. If you use the data in your research, we kindly ask that you reference the repository and the corresponding paper [1] A. Breger, J.Gröhl, C. Karner, T.R. Else, I. Selby, J. Weir-McCall, C.-B. Schönlieb: PhotIQA: A photoacoustic image data set with image quality ratings, preprint on arXiv: http://arxiv.org/abs/2507.03478 Update v3.0 (April 30, 2026): Quality ratings of 3 more experts have been added, now resulting in 5 expert ratings per image