Space Carving Acceleration Using Uncertainty Measurements

Authors:
M. Claudia Pérez;Miquel Casamitjana;Enric X. Martín
Affiliations:
Department of System Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain 08028;Department of System Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain 08028;Department of System Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain 08028
Venue:
IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis
Year:
2009

Citing 8
Cited 0

Plenoptic modeling: an image-based rendering system

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Photorealistic Scene Reconstruction by Voxel Coloring

International Journal of Computer Vision
A Theory of Shape by Space Carving

International Journal of Computer Vision - Special issue on Genomic Signal Processing
A Probabilistic Theory of Occupancy and Emptiness

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Generalized Voxel Coloring

ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Methods for Volumetric Reconstruction of Visual Scenes

International Journal of Computer Vision
Robust Carving for Non-Lambertian Objects

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Variational principles, surface evolution, PDEs, level set methods, and the stereo problem

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a method for obtaining a fast but rough 3D object reconstruction. This reconstruction will contain enough information to determine a minimum complementary view set that can refine it more accurately. Thus it is possible to take advantage of the space carving algorithm simplicity. This algorithm is fast and easy to accelerate by means of hardware and software techniques, but cannot easily manage the uncertainty derived from the segmentation process. In the proposed method, uncertainty is projected onto the voxels and computed with them when new views are processed. In this way, a measure of the reconstruction certainty is obtained, identifying the regions where more information is needed in order to be resolved.