CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
3-D Depth Reconstruction from a Single Still Image
International Journal of Computer Vision
Improved Single Image Dehazing Using Geometry
DICTA '09 Proceedings of the 2009 Digital Image Computing: Techniques and Applications
Hi-index | 0.00 |
Extracting 3D information from a 2D image has been a challenging task in the field of computer vision. Various approaches which use techniques like focusing/defocusing, shading, machine learning, and statistical methods and models, have been presented to extract such information. However, these approaches are computationally intensive. In this paper, a novel pixel based method is presented in which the interdependence between the atmospheric scattering and the distance of the object in an external outdoor scene is used. The method computes the attenuation coefficient from a scene image and uses it for generation of the depth image depicting relative ordering of objects in the image. The experimental results are encouraging w.r.t. the earlier methods.