yuri boykov research interests

Post on 03-Jan-2016

34 Views

Category:

Documents

4 Downloads

Preview:

Click to see full reader

DESCRIPTION

Combinatorial optimization algorithms Geometric, probabilistic, information theoretic, and physics based models. Yuri Boykov Research Interests. Computer Vision Medical Image Analysis Graphics. Geometric methods, combinatorial algorithms Segmentation. - PowerPoint PPT Presentation

TRANSCRIPT

The University of

Ontario

Yuri Boykov

Research Interests

Computer Vision

Medical Image Analysis

Graphics

Combinatorial optimization algorithms

Geometric, probabilistic, information theoretic, and

physics based models.

The University of

Ontario

Geometric methods, combinatorial algorithmsSegmentation

The University of

Ontario

Geometric methods, combinatorial algorithms Motion

beating heart

The University of

Ontario

Geometric methods, combinatorial algorithms Multi-view shape reconstruction

3D model

multi-view reconstruction set up

Furukawa&Ponce ECCV’06

The University of

Ontario

Geometric methods, combinatorial algorithms Multi-view shape reconstruction

3D model

multi-view reconstruction set up

Furukawa&Ponce ECCV’06

(texture mapped)

The University of

Ontario

Geometric methods, combinatorial algorithms Surface fitting

a cloud of 3D points (e.g. from a laser scanner)

3D model:

surface fitting:

The University of

Ontario

Geometric methods, combinatorial algorithms Texture synthesis

The University of

Ontario

Geometric methods, combinatorial algorithms model fitting

“left eye” image “right eye” image

The University of

Ontario

Geometric methods, combinatorial algorithmsmodel fitting

“left eye” image “right eye” image

fitted planes

The University of

OntarioGraduate courses

9587: Algorithms for Image Analysis (fall)• optimization algorithms in computer vision and

medical imaging

9837: Computer Vision for Graphics (winter)• graduate seminar• research papers from SIGGRAPH, ICCV, ECCV,CVPR

The University of

OntarioResearch (on a technical side)

Fast inference algorithms for Markov Random Fields

Global optimization in infinite-dimensional spaces (functions /surfaces)

Discrete metric spaces

Efficient combinatorial algorithms

...

The University of

OntarioCollaborations

University of Bonn, Germany University College London, UK Lund University, Sweden Oxford Brooks University, UK Moscow State University, Russia Ecole Nationale de Pont et Chaussese, Paris, France Microsoft Research, Cambridge, UK Siemens Research, Princeton, USA

top related