Supplementary Material Page for Our ECCV Paper

Joint Estimation of Motion, Structure and
Geometry from Stereo Sequences


Results for our Jenny Sequence


This page shows the results for our approach applied on our "Jenny" sequence. This is a real-world sequence that shows different facial expressions. A video with our results is shown below and can also be downloaded here [9.6 MB]. The scene flow is color coded, where green stands for small displacement vectors and red for large displacement vectors. The untextured result can be interpreted as a 3-dimensional variant of optical flow.

Please enable Javascript and Flash to see the video



Below we show detailed results of two expression: Smiling and Closing Mouth.


(1) Smiling

Left: Left image at time t. Right: Right image at time t+1.

Scene flow.

Overlay of reconstruction and scene flow.


Zoom in previous image.


(2) Closing Mouth

Left: Left image at time t. Right: Right image at time t+1.

Scene flow.

Zoom in overlay of reconstruction and scene flow.

Back -- Main Page



MIA Group
©2001-2023
The author is not
responsible for
the content of
external pages.

Imprint - Data protection