Antonio Haro

I am interested in  computer graphics/rendering, computer vision and perception, and future computing environments.

I received my Ph.D. from the College of Computing at Georgia Tech after performing research in the Computational Perception Lab.

My email address is

Current Research:

Cameras and Vision: How can mobile games use computer vision to enable new game experiences? (GDC Mobile 2006)
Vison-based adaptive viewing: Vision-based mobile user-interfaces permit one-handed operation of complex tasks such as media gallery browsing.
Mobile vision-based UIs: Computer vision-based tracking can be used to create richer user interfaces than with buttons alone. (Video here)

Prior Research:

Example based processing (Thesis): Example based processing can be used to create imagery using machine learning.
Exemplar based surface texture: Novice users can use a digital photograph of a source material to easily create photorealistic renderings of 3D models.
Learning video processing by example: This algorithm approximates the output of an arbitrary video processing algorithm based on a pair of input and output exemplars. The algorithm relies on learning the mapping between the input and output exemplars to model the processing that has taken place.
Fine-scale skin structure rendering: Rendering the fine structure present in skin adds significantly to its photo-realism.
Eye tracking: Finding and detecting eyes in real-time computationally inexpensively is important because it is a fundamental first step towards more attentive user interfaces.
Head tracking: Natural interaction with computers requires awareness of the head position and orientation of users. Head tracking can also be used to process video to add special effects to video streams.


Other things: