Accurate subpixel shifting of point spread functions

The localization of emitters requires accurate subpixel shifting of point spread function (PSF) models. However, the PSF recorded by the camera is not the true PSF of the system due to integration across finite pixels. These errors can be propagated during the shifting process, causing systematic biases in the registration or localization process. This letter proposes a set of filter kernels that, when convolved with the image, accurately shifts it by an arbitrary subpixel shift. Each pixel in the filter is represented by a two-dimensional polynomial function of the possible x and y shift values. These filters are effective; when tested on three different PSFs, they reduced errors by a factor of 20 or more over PSF models evaluated at the pixel center.