Internal Seminar: Prof. Jeppe Revall Frisvad, Technical University of Denmark
A big welcome to Prof. Jeppe Revall Frisvad from Technical University of Denmark who visited our Center! Today, he presents his work on "Glass Object Appearance Acquisition Using Learning-Based Inverse Rendering". Most rendering tools have the ability to produce plausible renderings of glass objects. However, such renderings are not necessarily photorealistic. At the Technical University of Denmark, Prof. Jeppe Revall Frisvad and collaborators are studing rendering techniques for making glass object photorealistic. With that, they can generate data set of synthetic images of glass objects with corresponding reference data. A large set of photorealistic synthetic images is useful for deep learning of the relation between glass appearance in a photograph and the shape and optical properties of the object. Prof. Jeppe Revall Frisvad gives us some indications of the performance of a convolutional neural network in acquiring the shape of a glass object from a photograph of it “in the wild”. We are greatful to prof. Jeppe Revall Frisvad, as his talk has activated discussion on how such an approach could be used for more accurate scanning of glass object shape when photographed in a robot-controlled light-camera configuration.