no code implementations • 22 Mar 2024 • Florian Langer, Jihong Ju, Georgi Dikov, Gerhard Reitmayr, Mohsen Ghafoorian
In contrast to previous works, we directly predict alignment parameters and shape embeddings.
no code implementations • 29 Jun 2023 • Kai-En Lin, Alex Trevithick, Keli Cheng, Michel Sarkis, Mohsen Ghafoorian, Ning Bi, Gerhard Reitmayr, Ravi Ramamoorthi
In this work, our goal is to take as input a monocular video of a face, and create an editable dynamic portrait able to handle extreme head poses.
no code implementations • ICCV 2023 • Xuepeng Shi, Georgi Dikov, Gerhard Reitmayr, Tae-Kyun Kim, Mohsen Ghafoorian
Self-supervised monocular depth estimation (SSMDE) aims at predicting the dense depth maps of monocular images, by learning to minimize a photometric loss using spatially neighboring image pairs during training.
no code implementations • 26 Jan 2022 • Ashar Ali, Upal Mahbub, Gokce Dane, Gerhard Reitmayr
In this paper, we present DIREG3D, a holistic framework for 3D Hand Tracking.
no code implementations • CVPR 2014 • Jonathan Ventura, Clemens Arth, Gerhard Reitmayr, Dieter Schmalstieg
We propose a novel solution to the generalized camera pose problem which includes the internal scale of the generalized camera as an unknown parameter.