Self-Calibration of Optical Lenses

Michael Hirsch, Bernhard Scholkopf; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 612-620

Even high-quality lenses suffer from optical aberrations, especially when used at full aperture. Furthermore, there are significant lens-to-lens deviations due to manufacturing tolerances, often rendering current software solutions like DxO, Lightroom, and PTLens insufficient as they don't adapt and only include generic lens blur models. We propose a method that enables the self-calibration of lenses from a natural image, or a set of such images. To this end we develop a machine learning framework that is able to exploit several recorded images and distills the available information into an accurate model of the considered lens.