1 / 24

1. Facial Expression Editing in Video Using a Temporally-Smooth Factorization

1. Facial Expression Editing in Video Using a Temporally-Smooth Factorization. 2. Face Swapping: Automatically Replacing Faces in Photographs. Facial Expression Editing in Video Using a Temporally-Smooth Factorization.

kyros
Télécharger la présentation

1. Facial Expression Editing in Video Using a Temporally-Smooth Factorization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. 1. Facial Expression Editing in Video Using a Temporally-Smooth Factorization 2. Face Swapping: Automatically Replacing Faces in Photographs

  2. Facial Expression Editing in Video Using a Temporally-Smooth Factorization FeiYang, LubomirBourdev, Eli Shechtman, JueWang, DimitrisMetaxas CVPR 2012

  3. Goal The goal is to allow for semantic-level editing of expressions in a video: • magnifying an expression • suppressing an expression • replacing by another expressions

  4. Example

  5. Challenges • Natural expression • Different parts changes accordingly • Unique identity • Temporal coherency

  6. Related Work • 2D based methods • [Theobald09], [Liu01], [Williams90], … • 3D based methods • [Blanz03], [Pighin98], … • Expression flow • [Yang11]… • Frame reorder method • [Bregler98], [Kemelmacher- Shlizerman11] • Tensor factorization methods • [Vlasic05], [Dale11]…

  7. Algorithm 3D Tensor Model - [Vlasic et al siggraph05] Modify Expression Information Identity Information

  8. Mode-n Product

  9. Algorithm goal to identify a and 2D v.s. 3D method = Weak Projective Matrix Rt frame t Minimize: | – |

  10. Algorithm Fitting Error: Shape Distribution Constraint: Temporal coherence:

  11. Algorithm Levenberg-Marquardt (Siggraph98)

  12. Algorithm Adjust to achieve expression modification • Dynamic Time Warping (DTW) [Sakoe78] • Residual Expression Flow • Correcting boundary compatibility

  13. Results

  14. Face Swapping: Automatically Replacing Faces in Photographs Dmitri BitoukNeeraj Kumar SamreenDhillon Peter Belhumeur Shree K. Nayar Siggraph 2008

  15. Examples

  16. Goals For an input image: • Automatically find the best candidate • Automatically replace the face • Automatically color and lighting adjustmet

  17. Library Building OKAO face detector to detect face pose [Omron07]

  18. Process

  19. Alignment Pose, Resolution, and Image Blur: • Yaw, pitch threshold between two images ( ) • Eye distance as a measure of distance (80%) • Similarity of the blur degrees [Kundur and Hatzinakos 1996; Fergus et al. 2006]

  20. Color and Lighting To ensure the similarity between the replaced and original face, a linear combination of 9 spherical harmonics [Ramamoorthi and Hanrahan 2001; Basri and Jacobs 2003] is used as measure metric: Each pixel I(x, y) can be approximated by: Distance:

  21. Seam Signature 256-by-256 patch from the face is used for replacement. Unfold: L2 Norm is used to compute the distance

  22. Appearance Adjustment Using simple scaling on the Harmonics coefficients , are the original and replacement images Scale the replaced image

  23. Results

  24. The End Any Questions ?

More Related