We present a novel representation and rendering method for free-viewpoint video of human characters based on multiple input video streams. The basic idea is to approximate the art...
Marcel Germann, Alexander Hornung, Richard Keiser,...
It is difficult to obtain a specific region within unsegmented volume data (region of interest, ROI). The user must first segment the volume, a task which itself involves signi...
Algorithms that detect silhouettes, creases, and other edge based features often perform per-edge and per-face mesh computations using global adjacency information. These are unsu...
Abstract. Human perception of shape is based on visual parts of objects to a point that a single, significant visual part is sufficient to recognize the whole object. For example,...
We present a simple technique for creating fluid silhouettes described with vector graphics, which we call ”Vector Fluid.” In our system, a solid region in the fluid is repr...