Advanced Search   
  Look in
       Name    Email
       Former RI Members 
Simon Baker
Adjunct Faculty, RI
No longer a member of RI.
Research Interests

I do computer vision. Within this field, I am particularly interested in the following areas:


Real-Time Non-Rigid Face Tracking / Active Appearance Model Fitting:
2D and 3D Face Model Building:
Resolution Enhancement / Hallucinating Faces:
Face Databases / PIE:
Face Recognition Across Pose / Eigen Light-Fields:
Gaze Estimation

3D Reconstruction and Vision/Graphics:

Fundamental Theorem of 3D Vision:
Shape-From-Silhouette Across Time:
Human Kinematic Modeling:
Human Articulated Tracking / Markerless Motion Capture:
Markerless Motion Transfer:
Scene Flow:
Spatio-Temporal View Interpolation:
Textureless Layers

Vision Theory:

Fundamental Theorem of 3D Vision:
Efficient Image Alignment / Lucas-Kanade 20 Years On Unifying Framework:
Fundamental Limits on Super-Resolution:
Light-Fields / Theoretical Properties for Stereo and Face Recognition
Textureless Layers

Vision for Safe Driving:

Danger Detection / Prediction and Planning:
Robust Car Tracking:
Bird's Eye View Generation:
Driver Head Tracking:
Driver Gaze Estimation


Theoretical Limits:
Hallucinating Faces:
Super-Resolution Optical Flow


Projector-Camera Systems / Tele-Graffiti:
Catadioptric Camera Design:
Feature Detection:
The Template Update Problem:
Automatic Construction of Active Appearance Models:
Setting Low-Level Vision Parameters

I work with a variety of different faculty, students, staff, visitors, and alumni including:

Adrian Broadhurst,
Vijayakumar Bhagavatula,
German Cheung,
Jeff Cohn,
Bob Collins,
Fernando de la Torre,
Ralph Gross,
Jessica Hodgins,
Changbo Hu,
Takahiro Ishikawa,
Takeo Kanade,
Qifa Ke,
Iain Matthews,
Andreas Nowatzyk,
Raju Patil,
Jeff Schneider,
Steve Seitz,
Jianbo Shi,
Terence Sim,
Jake Sprouse,
Naoya Takao,
David Tolliver,
Sundar Vedula,
Jing Xiao

Please see the projects below for more details.

Research Interest Keywords
computer visionobject recognitionpattern recognitionsensorsstereo visionvisual tracking