Christian Theobalt

TL;DR: Face2Face as mentioned in this paper is an approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video) by animating the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion.

TL;DR: LidarBoost is presented, a 3D depth superresolution method that combines several low resolution noisy depth images of a static scene from slightly displaced viewpoints, and merges them into a high-resolution depth image.

TL;DR: This work proposes a novel two-stage analysis-by-synthesis optimization whose formulation and implementation are designed for high performance, and is the first real-time monocular approach for full-body performance capture.

TL;DR: In this paper, a multi-garment network (MGN) is proposed to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses.

TL;DR: A detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed is provided in this paper, where the challenges in building and applying these models, namely, capture, modeling, image formation, and image analysis, are still active research topics, and the state-of-the-art in each of these areas are reviewed.