Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques
Ruggero Pintus, Andrea Giachetti, Gianni Pintore and Enrico Gobbetti
Abstract
The generation of a basic matte model is at the core of many multi-light reflectance
processing approaches, such as Photometric Stereo or Reflectance Transformation Imaging. To recover information on objects’ shape and appearance, the matte model is used
directly or combined with specialized methods for modeling high-frequency behaviors.
Multivariate robust regression offers a general solution to reliably extract the matte component when source data is heavily contaminated by shadows, inter-reflections, specularity, or noise. However, robust multivariate modeling is usually very slow. In this paper,
we accelerate robust fitting by drastically reducing the number of tested candidate solutions using a guided approach. Our method propagates already known solutions to nearby
pixels using a similarity-driven flood-fill strategy, and exploits this knowledge to order
possible candidate solutions and to determine convergence conditions.
Session
Posters
Files
Paper (PDF)
DOI
10.5244/C.31.32
https://dx.doi.org/10.5244/C.31.32
Citation
Ruggero Pintus, Andrea Giachetti, Gianni Pintore and Enrico Gobbetti. Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 32.1-32.15. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_32,
title={Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques},
author={Ruggero Pintus, Andrea Giachetti, Gianni Pintore and Enrico Gobbetti},
year={2017},
month={September},
pages={32.1-32.15},
articleno={32},
numpages={15},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.32},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.32}
}