• Publications
  • Influence
Fast Approximate Energy Minimization via Graph Cuts
TLDR
We present two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves. Expand
  • 4,773
  • 462
Fast approximate energy minimization via graph cuts
TLDR
In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. Expand
  • 3,083
  • 257
  • PDF
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done onExpand
  • 2,303
  • 202
What Energy Functions Can Be Minimized via Graph Cuts?
TLDR
We give a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables. Expand
  • 2,297
  • 166
Image indexing using color correlograms
TLDR
We define a new image feature called the color correlogram and use it for image indexing and comparison. Expand
  • 1,883
  • 144
  • PDF
Non-parametric Local Transforms for Computing Visual Correspondence
TLDR
We propose a new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation, and demonstrate their utility on both synthetic and real data. Expand
  • 1,751
  • 124
  • PDF
Computing visual correspondence with occlusions using graph cuts
TLDR
We present a new graph cut algorithm for visual correspondence that handles occlusions properly, while maintaining the key advantages of graph cuts. Expand
  • 1,251
  • 123
  • PDF
What energy functions can be minimized via graph cuts?
  • V. Kolmogorov, R. Zabih
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 28 May 2002
TLDR
We give a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables. Expand
  • 1,605
  • 109
  • PDF
Multi-camera Scene Reconstruction via Graph Cuts
TLDR
We address the problem of computing the 3-dimensional shape of an arbitrary scene from a set of images taken at known viewpoints. Expand
  • 851
  • 91
  • PDF
A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors
TLDR
We describe a set of energy minimization benchmarks and use them to compare the solution quality and runtime of several commonenergy minimization algorithms. Expand
  • 1,012
  • 89
  • PDF