Graphics enhanced version of this site

Face Video Hallucination
Head: Goksel Dedeoglu
Contact: Goksel Dedeoglu

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated center: VASC
Associated lab/group: Face Group

This page last updated - January 1999.

We developed a learning-based super-resolution algorithm that can achieve 16-fold improvement in resolution. We use a database of facial expression videos as a domain-specific prior, and pose the problem of resolution enhancement as one of probabilistic inference. Our results show that by exploiting both spatial and temporal consistencies, hallucinated videos can be rendered more stable and accurate.

Preliminary Results [CVPR '04 Paper]

Name - Title <Email Address>
• [Home] Takeo Kanade - U.A. and Helen Whitaker University Prof., RI/CS <tk@cs.cmu.edu>

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Exploiting Space-Time Statistics of Videos for Face “Hallucination”
  G. Dedeoglu
  doctoral dissertation, tech. report CMU-RI-TR-07-05, Robotics Institute, Carnegie Mellon University, April, 2007. [Abstract]
  Download: pdf [12988 KB] copyrighted

• High-Zoom Video Hallucination by Exploiting Spatio-Temporal Regularities
  G. Dedeoglu, T. Kanade, and J. August
  Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '04), Vol. 2, June, 2004, pp. 151 - 158. [Abstract]
  Download: pdf [503 KB] copyrighted