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 goal is to learn a deep network that, given a small number of images of an object of a given category, reconstructs it in 3D.
We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance.
no code implementations • 20 Nov 2020 • Philipp Henzler, Christian Traum, Matthias Holtkemper, David Nabben, Marcel Erbe, Doris E. Reiter, Tilmann Kuhn, Suddhassatta Mahapatra, Karl Brunner, Denis V. Seletskiy, Alfred Leitenstorfer
Ultrafast transmission changes around the fundamental trion resonance are studied after exciting a p-shell exciton in a negatively charged II-VI quantum dot.
Mesoscale and Nanoscale Physics Quantum Physics
We can successfully reconstruct 3D shapes from unstructured 2D images and extensively evaluate PlatonicGAN on a range of synthetic and real data sets achieving consistent improvements over baseline methods.
We tackle the problem of object detection and pose estimation in a shared space downtown environment.