Abstract

Estimating geometric structure from uncalibrated images ac- curately enough for high quality rendering is dificult. We present a method where only coarse geometric structure is tracked and estimated from a moving camera. Instead a precise model of the intensity image variation is obtained by overlaying a dynamic, time varying texture on the structure. This captures small scale variations (e.g. non-planarity of the rendered surfaces, small camera geometry distortions and tracking errors). The dynamic texture is estimated and coded much like in movie compression, but parameterized in 6D pose instead of time, hence allow- ing the interpolation and extrapolation of new poses in the rendering and animation phase. We show experiments tracking and re-animating natural scenes as well as evaluating the geometric and image intensity accuracy on constructed special test scenes.