Y
Yuri Boykov
Researcher at University of Waterloo
Publications - 124
Citations - 32510
Yuri Boykov is an academic researcher from University of Waterloo. The author has contributed to research in topics: Image segmentation & Cut. The author has an hindex of 44, co-authored 124 publications receiving 29588 citations. Previous affiliations of Yuri Boykov include Carnegie Mellon University & University of Western Ontario.
Papers
More filters
Proceedings ArticleDOI
Global Optimization for Shape Fitting
Victor Lempitsky,Yuri Boykov +1 more
TL;DR: A touch-expand algorithm for finding a minimum cut on a huge 3D grid using an automatically adjusted band overcomes prohibitively high memory cost of graph cuts when computing globally optimal surfaces at high-resolution.
Proceedings ArticleDOI
Globally optimal segmentation of multi-region objects
Andrew Delong,Yuri Boykov +1 more
TL;DR: This work shows how to encode geometric interactions between distinct region+boundary models, such as regions being interior/exterior to each other along with preferred distances between their boundaries, and applications in medical segmentation and scene layout estimation.
Proceedings ArticleDOI
Applications of parametric maxflow in computer vision
TL;DR: Algorithmic aspects of this parametric maximum flow problem previously unknown in vision, such as the ability to compute all breakpoints of lambda and corresponding optimal configurations infinite time are reviewed.
Proceedings ArticleDOI
A Scalable graph-cut algorithm for N-D grids
Andrew Delong,Yuri Boykov +1 more
TL;DR: This work enhances the push-relabel algorithm for maximum flow with two practical contributions: first, true global minima can now be computed on immense grid-like graphs too large for physical memory, and for commodity multi-core platforms the algorithm attains near-linear speedup with respect to number of processors.
for Optimal Boundary & Region Segmentation of Objects in N-D Images
Yuri Boykov,Marie-Pierre Jolly +1 more
TL;DR: A new technique for general purpose interactive segmentation of N-dimensional images where the user marks certain pixels as "object" or "background" to provide hard constraints for segmentation.