Research >> Multiscale terms

 

Multiscale terms

 

Multiscale terms are often seen to improve the performance of
algorithms. In this work, we show how to incorporate multiscale
terms within the graph cuts framework, and show the effectiveness
of this approach for a variety of computer vision problems, including optical
flow, segmentation, and image restoration.

 

Faculty: Daniel Freedman

Student: Matt Turek

 

 


Home | People | Research | Publications | Contact | News/Events | Download | Links