Abstract. Using silhouettes in uncontrolled environments typically requires handling occlusions as well as changing or cluttered backgrounds, which limits the applicability of most...
This paper proposes a method for capturing the performance
of a human or an animal from a multi-view video
sequence. Given an articulated template model and silhouettes
from a m...
Juergen Gall (BIWI, ETH Zurich), Carsten Stoll (Ma...
We present a novel algorithm to jointly capture the motion and the dynamic shape of humans from multiple video streams without using optical markers. Instead of relying on kinemat...
Edilson de Aguiar, Christian Theobalt, Carsten Sto...
Detection and analysis of ocean surface phenomena have so far relied on manual analysis of long sequences of satellite images or images produced from the mathematical models. In t...
Veena Moolani, Ramprasad Balasubramanian, Li Shen,...
The key to real-time rendering of large-scale surfaces is to locally adapt surface geometric complexity to changing view parameters. Several schemes have been developed to address...