A fast method for global depth-map extraction from natural images

Authors:
Vamsidhar Reddy;Alexander Eichhorn;Jon Yngve Hardeberg;Raju Shrestha
Affiliations:
Gjøvik University College, Gjøvik, Norway;Simula Research Laboratory, Oslo, Norway;Gjøvik University College, Gjøvik, Norway;Gjøvik University College, Gjøvik, Norway
Venue:
Proceedings of the 9th European Conference on Visual Media Production
Year:
2012

Citing 11
Cited 0

A new approach to the maximum flow problem

STOC '86 Proceedings of the eighteenth annual ACM symposium on Theory of computing
Visual reconstruction

Visual reconstruction
Experimental study of minimum cut algorithms

SODA '97 Proceedings of the eighth annual ACM-SIAM symposium on Discrete algorithms
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
What Energy Functions Can Be Minimizedvia Graph Cuts?

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Belief Propagation for Early Vision

International Journal of Computer Vision
A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Free-viewpoint depth image based rendering

Journal of Visual Communication and Image Representation
High-accuracy stereo depth maps using structured light

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Depth Estimation from Three Cameras Using Belief Propagation: 3D Modelling of Sumo Wrestling

CVMP '11 Proceedings of the 2011 Conference for Visual Media Production

Quantified Score

Hi-index	0.00

Visualization

Abstract

Dense depth-map extraction approaches either suffer from limited accuracy and robustness when run on natural images or from long computation times due to complex global optimizations. Recent improvements in massively parallel execution architectures found in today's graphics processing units motivated us to parallelize the global optimization process. In this article we present our analytical approach and a parallel implementation in OpenCL of a multi-label graph-cut algorithm. Our approach accomodates a third camera perspective through which we can improve occlusion handling in order to generate high quality depth maps. Through experiments on natural images we show that our implementation scales linearly and achieves close-to realtime performance.