De-Rendering the World's Revolutionary Artefacts

Input Albedo Diffuse Specular Material Env. map Normal Novel view Single image collection Training Inference Relight Figure 1: De-rendering from single images. From only a real single-view image collection of "revolutionary" (i.e., solid of revolution) artefacts with known silhouettes as training data (left), our framework learns to de-render a single image into shape, albedo and complex lighting and material components, suitable for applications such as novel-view synthesis and relighting (right).