Abstract: Despite the widespread use of measured real-world materials, intuitive tools for editing measured reflectance datasets are still lacking. We present a solution inspired by natural image matting and texture synthesis to the material matting problem, which allows separating a measured spatially-varying material into simpler foreground and background component materials and a corresponding opacity map. We approach this problem in the context of Bayesian statistics and introduce a new prior on materials that favors those with highly self-similar stochastic structure. We describe a prototype system that iteratively performs these separations based on small sets of user scribbles and demonstrate multiple separations and edits.