| Paper: | TA-P8.8 |
| Session: | Image and Video Restoration and Enhancement II |
| Time: | Tuesday, September 18, 09:50 - 12:30 |
| Presentation: |
Poster
|
| Title: |
SUPER-RESOLVED FACIAL TEXTURE UNDER CHANGING POSE AND ILLUMINATION |
| Authors: |
Jiangang Yu; University of California, Riverside | | |
| | Bir Bhanu; University of California, Riverside | | |
| | Yilei Xu; University of California, Riverside | | |
| | Amit K. Roy-Chowdhury; University of California, Riverside | | |
| Abstract: |
In this paper, we propose a method to incrementally super-resolve 3D facial texture by integrating information frame by frame from a video captured under changing poses and illuminations. First, we recover illumination, 3D motion and shape parameters from our tracking algorithm. This information is then used to super-resolve 3D texture using Iterative Back-Projection (IBP) method. The super-resolved texture, in turn, is fed back to our tracking part to improve the estimation of illumination and motion parameters. This closed-loop process continues to refine the texture as new frames come in. We also propose a local-region based scheme to handle non-rigidity of human face. Experiments demonstrate that our framework not only incrementally super-resolves facial images, but recovers the detailed expression changes in high quality. |
