pdf

Piecewise Planar Stereo for Image-based Rendering
  • Piecewise Planar Stereo for Image-based Rendering
Gallery
research.microsoft.com
We present a novel multi-view stereo method designed for image-based rendering that generates piecewise planar depth maps from an unordered collection of photographs. First a discrete set of 3D plane candidates are computed based on a sparse point cloud of the scene (recovered by structure from motion) and sparse 3D line segments reconstructed from multiple views....
Sudipta N. Sinha, Drew Steedly and Richard Szeliski
ICCV - 2009
IEEE
pdf

Face Recognition With Contiguous Occlusion Using Markov Random Fields
  • Face Recognition With Contiguous Occlusion Using Markov Random Fields
claim it Gallery
perception.csl.uiuc.edu
Partially occluded faces are common in many applications of face recognition. While algorithms based on sparse representation have demonstrated promising results, they achieve their best performance on occlusions that are not spatially correlated (i.e. random pixel corruption)....
Zihan Zhou, Andrew Wagner, Hossein Mobahi, John Wright, Yi Ma
ICCV - 2009
IEEE
pdf

Beyond Pairwise Energies: Efficient Optimization for Higher-order MRFs
  • Beyond Pairwise Energies: Efficient Optimization for Higher-order MRFs
claim it Gallery
www.csd.uoc.gr
In this paper, we introduce a higher-order MRF optimization framework....
Nikos Komodakis, Nikos Paragios
CVPR - 2009
IEEE
pdf

Continuous Maximal Flows and Wulff Shapes: Application to MRFs
  • Continuous Maximal Flows and Wulff Shapes: Application to MRFs
claim it Gallery
www.cs.unc.edu
Convex and continuous energy formulations for low level vision problems enable efficient search procedures for the corresponding globally optimal solutions....
Christopher Zach, Marc Niethammer, Jan-Michael Frahm
CVPR - 2009
IEEE
pdf

Learning Real-Time MRF Inference for Image Denoising
  • Learning Real-Time MRF Inference for Image Denoising
claim it Gallery
stat.fsu.edu
Many computer vision problems can be formulated in a Bayesian framework with Markov Random Field (MRF) or Conditional Random Field (CRF) priors. Usually, the model assumes that a full Maximum A Posteriori (MAP) estimation will be performed for inference, which can be really slow in practice....
Adrian Barbu
CVPR - 2009
IEEE
pdf

A Revisit of Generative Model for Automatic Image Annotation using Markov Random Fields
  • A Revisit of Generative Model for Automatic Image Annotation using Markov Random Fields
claim it Gallery
lms.comp.nus.edu.sg
Much research effort on Automatic Image Annotation (AIA) has been focused on Generative Model, due to its well formed theory and competitive performance as compared with many well designed and sophisticated methods. However, when considering semantic context for annotation, the model suffers from the weak learning ability....
Yu Xiang, Xiangdong Zhou, Tat-Seng Chua, Chong-Wah Ngo
CVPR - 2009
IEEE
pdf

Global Connectivity Potentials for Random Field Models
  • Global Connectivity Potentials for Random Field Models
claim it Gallery
www.kyb.mpg.de
Markov random field (MRF, CRF) models are popular in computer vision. However, in order to be computationally tractable they are limited to incorporate only local interactions and cannot model global properties, such as connectedness, which is a potentially useful high-level prior for object segmentation....
Sebastian Nowozin, Christoph Lampert
CVPR - 2009
IEEE
pdf

Learning Optimized MAP Estimates in Continuously-Valued MRF Models
  • Learning Optimized MAP Estimates in Continuously-Valued MRF Models
claim it Gallery
www.cs.ucf.edu
We present a new approach for the discriminative training of continuous-valued Markov Random Field (MRF) model parameters. In our approach we train the MRF model by optimizing the parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth....
Kegan Samuel, Marshall Tappen
CVPR - 2009
IEEE
pdf

Introduction to Statistical Signal Processing
  • Introduction to Statistical Signal Processing
ee.stanford.edu
"A random or stochastic process is a mathematical model for a phenomenon that evolves in time in an unpredictable manner from the viewpoint of the observer....
R.M. Gray
pdf

Markov Random Field Modeling in Computer Vision
  • Markov Random Field Modeling in Computer Vision
www.cbsr.ia.ac.cn
Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems....
Stan Z. Li
12 next › last »