A probabilistic framework for space carving
- 13 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 388-393
- https://doi.org/10.1109/iccv.2001.937544
Abstract
This paper introduces a new probabilistic framework for Space Carving (9). In this framework each voxel is as- signed a probability, which is computed by comparing the likelihoods for the voxel existing and not existing. This new framework avoids many of the difficulties asso- ciated with the original Space Carving algorithm. Specifi- cally, it does not need a global threshold parameter, and it guarantees that no holes will be carved in the model. This paper also proposes that a voxel-based thick texture is a re- alistic and efficient representation for scenes which contain dominant planes. The algorithm is tested using both real and synthetic data, and both qualitative and quantitative results are presented.Keywords
This publication has 9 references indexed in Scilit:
- Stereo matching with transparency and mattingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A layered approach to stereo reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Theory of Shape by Space CarvingInternational Journal of Computer Vision, 2000
- Photorealistic Scene Reconstruction by Voxel ColoringInternational Journal of Computer Vision, 1999
- Fast approximate energy minimization via graph cutsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Variational principles, surface evolution, PDEs, level set methods, and the stereo problemIEEE Transactions on Image Processing, 1998
- Modeling and rendering architecture from photographsPublished by Association for Computing Machinery (ACM) ,1996
- A stereo matching algorithm with an adaptive window: theory and experimentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Cooperative Computation of Stereo DisparityScience, 1976