Abstract: Rough refraction commonly occurs when light scatters on rough transparent surfaces. It presents a computational challenge, as every pixel's color depends on incoming light from numerous directions. De Rousiers et al. [2011] compute rough refraction interactively using a convolution of Gaussian normal and transmittance distribution functions (NDFs and BTDFs), but their work is limited to a constant roughness surfaces. We introduce two methods that allow for varying roughness by representing surface normals using LEAN mapping and Gaussian sum reduction (GSR).