Abstract
We propose a material classification method using rawtime-of-flight (ToF) measurements. ToF cameras capturethe correlation between a reference signal and the temporalresponse of material to incident illumination. Such mea-surements encode unique signatures of the material, i.e.the degree of subsurface scattering inside a volume. Sub-sequently, it offers an orthogonal domain of feature rep-resentation compared to conventional spatial and angularreflectance-based approaches. We demonstrate the effec-tiveness, robustness, and efficiency of our method throughexperiments and comparisons of real-world materials.