Christian Theobalt

TL;DR: This work proposes a new efficient single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera that succeeds even under strong partial body occlusions by other people and objects in the scene.

TL;DR: An overview on the state of the art in full body human motion capture using depth cameras is given, elaborate on the challenges current algorithms face and discuss possible solutions, and investigates how the integration of additional sensor modalities may help to resolve some of the ambiguities and improve tracking results.

TL;DR: The first approach for the decomposition of a monocular color video into direct and indirect illumination components in real time is proposed and improvements over the state-of-the-art in this field are shown, in both quality and runtime.

TL;DR: In this article, a real-time pose and shape reconstruction of two strongly interacting hands is presented, which combines an extensive list of favorable properties, namely it is markerless, uses a single consumer-level depth camera, runs in real time, handles inter-and intra-hand collisions, and automatically adjusts to the user's hand shape.

TL;DR: NeuS2 as mentioned in this paper integrates multi-resolution hash encodings into a neural surface representation and implements the whole algorithm in CUDA, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality.