Disparity and normal estimation through alternating maximization

Ramya Narasimha 1 Elise Arnaud 2 Florence Forbes 3 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 STEEP - Sustainability transition, environment, economy and local policy
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
3 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper, we propose an algorithm that recovers binocular disparities in accordance with the surface properties of the scene under consideration. To do so, we estimate the disparity as well as the normals in the disparity space, by setting the two tasks in a unified framework. A novel joint probabilistic model is defined through two random fields to favor both intra field (within neighboring disparities and neighboring normals) and inter field (between disparities and normals) consistency. Geometric contextual information is introduced in the models for both normals and disparities, which is optimized using an appropriate alternating maximization procedure. We illustrate the performance of our approach on synthetic and real data.
Keywords : Alternating Maximization CRF MRF Stereo Vision
Document type :
Conference papers
ICIP 2010 - 17 IEEE International Conference on Image Processing, Sep 2010, Honk Kong, China. IEEE, pp.2969-2972, 2010, 〈10.1109/ICIP.2010.5653453〉
Liste complète des métadonnées

surfaces.jpg
surfaces.jpg
https://hal.inria.fr/inria-00517864
Contributor : Elise Arnaud <>
Submitted on : Wednesday, September 15, 2010 - 5:19:36 PM
Last modification on : Wednesday, April 11, 2018 - 1:59:07 AM
Document(s) archivé(s) le : Friday, December 2, 2016 - 1:56:40 AM

Files

icip10_final3382.pdf
Files produced by the author(s)

Identifiers

Collections

INRIA | LJK_GI | LJK_PS | LJK_GI_PERCEPTION | LJK_MAD_STEEP | LJK_PS_MISTIS | LJK_MAD | LJK | UGA

Citation

Ramya Narasimha, Elise Arnaud, Florence Forbes, Radu Horaud. Disparity and normal estimation through alternating maximization. ICIP 2010 - 17 IEEE International Conference on Image Processing, Sep 2010, Honk Kong, China. IEEE, pp.2969-2972, 2010, 〈10.1109/ICIP.2010.5653453〉. 〈inria-00517864〉

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

568

Files downloads

435

Contact


archive-ouverte@inria.fr