Learn More
Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified(More)
This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers,(More)
There is a huge diversity of definitions of “visually meaningful” image segments, ranging from simple uniformly colored segments, textured segments, through symmetric patterns, and up to complex semantically meaningful objects. This diversity has led to a wide range of different approaches for image segmentation. In this paper we present a single unified(More)
Clustering is a fundamental task in unsupervised learning. The focus of this paper is the Correlation Clustering functional which combines positive and negative affinities between the data points. The contribution of this paper is two fold: (i) Provide a theoretic analysis of the functional. (ii) New optimization algorithms which can cope with large scale(More)
Given very few images containing a common object of interest under severe variations in appearance, we detect the common object and provide a compact visual representation of that object, depicted by a binary sketch. Our algorithm is composed of two stages: (i) Detect a mutually common (yet non-trivial) ensemble of ‘self-similarity(More)
  • S. Bagon
  • 2012 International Conference on Information…
  • 2012
This paper presents a novel approach and interface to interactive image segmentation. Our interface uses sparse and inaccurate boundary cues provided by the user to produce a multi-layer segmentation of the image. Using boundary cues allows our interface to utilize a single "boundary brush" to produce a multi-layer segmentation, making it appealing for(More)
In this thesis I explore challenging discrete energy minimization problems that arise mainly in the context of computer vision tasks. This work motivates the use of such “hard-to-optimize” non-submodular functionals, and proposes methods and algorithms to cope with the NP-hardness of their optimization. Consequently, this thesis revolves around two axes:(More)
As mentioned in the paper, in this supplementary document we describe experimental details that were omitted from the main paper for reasons of clarity and space. Additionally, we remind the reader of the the Gibbs sampler and the minimization via Simulated annealing (SA) that we use for inference. 1. Additional Experiment: Generic Object Class Recognition(More)