Comparison to Thies et al. [2016]
-- our result is on the right --

1 2 3 4 5 6
Input Target
Driving Video
[Thies et al. 2016]
Our Result

Comparison to previous reenactment work by replicating the single target image to form a video. As these results demonstrate, in previous work, the head cannot the move, and the generated expressions are significantly less natural-appearing.

[Thies et al. 2016] Face2face: Real-time face capture and reenactment of rgb videos. Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., and Niessner, M.

Back to previous page