International Journal of Computer Vision
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Sparse Scene Structure Recovery from Atmospheric Degradation
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
In computer vision, the majority of research works covering the subject of vision through participating media are based on the concept of single scattering of light rays. Only few works deal with multiple scattering and they do so under restrictive constraints. In this paper we introduce a new multiple-scattering based polychromatic model (PM) for vision through participating media. This model involves two basic concepts, namely attenuation and ambient illumination. The resulting model can be applied to a wide range of media. For instance, it can be devoted to the modeling of atmospheric vision, underwater vision and vision through misty glass. We show that it can be used to accurately restore the original versions of degraded images taken through atmosphere. Experimental results confirm that the proposed model is both in good agreement with the theory, and useful in practice.