Inferring 3D shape and appearance from natural images is a fundamental challenge in computer vision. Despite recent progress using deep learning methods, a key limitation is the availability of annotated training data, as acquisition is often very …
Traditional approaches for learning 3D object categories have been predominantly trained and evaluated on synthetic datasets due to the unavailability of real 3D-annotated category-centric data. Our main goal is to facilitate advances in this field …
We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flash light illumination, first it is converted …