In this paper we present SurfaceNet, an approach for estimatingspatially-varying bidirectional reflectance distribution function (SVBRDF)material properties from a single image . We pose the problem as an imagetranslation task and propose a novel patch-based generative adversarial network that is able to produce high-quality, high-resolution surface reflectancemaps . An extensive evaluation, carried out on a public benchmark ofsynthetic and real images under different illumination conditions, shows that SurfaceNet largely outperforms existing SVBRDF reconstruction methods, bothquantitatively and qualitatively .

Author(s) : Giuseppe Vecchio, Simone Palazzo, Concetto Spampinato

Links : PDF - Abstract

Code :

Keywords : svbrdf - surfacenet - high - adversarial - image -

Leave a Reply

Your email address will not be published. Required fields are marked *