Carved Visual Hulls for Image-Based Modeling
International Journal of Computer Vision
Improving Border Localization of Multi-Baseline Stereo Using Border-Cut
International Journal of Computer Vision
The Vision System of the ACROBOTER Project
ICIRA '09 Proceedings of the 2nd International Conference on Intelligent Robotics and Applications
An occupancy-depth generative model of multi-view images
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Temporal priors for novel video synthesis
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
A speeded-up local descriptor for dense stereo matching
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Surface reconstruction from images using a variational formulation
MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling
An optimal time---space algorithm for dense stereo matching
Journal of Real-Time Image Processing
Incremental 3d reconstruction using bayesian learning
IEA/AIE'12 Proceedings of the 25th international conference on Industrial Engineering and Other Applications of Applied Intelligent Systems: advanced research in applied artificial intelligence
SCoBeP: Dense image registration using sparse coding and belief propagation
Journal of Visual Communication and Image Representation
Image-based reconstruction and synthesis of dense foliage
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
An efficient image matching method for multi-view stereo
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Incremental 3D reconstruction using Bayesian learning
Applied Intelligence
Hi-index | 0.00 |
In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier process, which generates the pixels which are visible from the reference camera and which obey the constant brightness assumption, and (ii) an outlier process which generates all other pixels. Depth and visibility are jointly modelled as a hiddenMarkov Random Field, and the spatial correlations of both are explicitly accounted for. Inference is made tractable by an EM-algorithm, which alternates between estimation of visibility and depth, and optimisation of model parameters. We describe and compare two implementations of the E-step of the algorithm, which correspond to the Mean Field and Bethe approximations of the free energy. The approach is validated by experiments on challenging real-world scenes, of which two are contaminated by independently moving objects.