Christian Theobalt

TL;DR: The present techniques make full-range 3D data available at video frame rates, and thus pave the way for a much broader application of 3D vision systems.

TL;DR: In this article, a method for generating video-realistic animations of real humans under user control is proposed, which relies on a video sequence in conjunction with a controllable 3D template model of the person.

TL;DR: It is discovered that transition preference varies with view change, that automatic rendered transitions are significantly preferred even with some artifacts, and that dissolve transitions are comparable to less-sophisticated rendered transitions.

TL;DR: This paper proposed a hierarchical two-stream sequential model to explore a finer joint-level mapping between natural language sentences and 3D pose sequences corresponding to the given motion, which can generate plausible pose sequences for short sentences describing single actions and long compositional sentences describing multiple sequential and superimposed actions.

TL;DR: In this article, the authors propose a method that disentangles the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space.