Christian Theobalt

TL;DR: This work quantitatively and qualitatively shows that the monocular approach reconstructs higher quality lip shapes, even for complex shapes like a kiss or lip rolling, than previous monocular approaches, and generalizes to new individuals and general scenes, enabling high-fidelity reconstruction even from commodity video footage.

TL;DR: In this paper, a fully automatic algorithm that jointly creates a rigged actor model commonly used for animation - skeleton, volumetric shape, appearance, and optionally a body surface - and estimates the actor's motion from multi-view video input only is proposed.

TL;DR: A compositional neural network is designed that predicts the silhouette, garment labels, and textures of a person and is used to synthesize human animations that can preserve the identity and appearance of the person in a temporally coherent way without any fine-tuning of the network on the testing scene.

TL;DR: A novel algorithm that robustly tracks 3D trajectories of features on a moving human who has been recorded with multiple video cameras is presented, which opens the door to new applications in motion capture, 3D Video and computer animation.

TL;DR: A novel approach is presented that estimates a hierarchical skeleton model of an arbitrary moving subject from sequences of voxel data that were reconstructed from multi-view video footage that does not require a-priori information about the body structure.