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