An efficient spatial domain technique for subpixel image registration
Image Communication
Computer Vision and Image Understanding
Improving sub-pixel accuracy for long range stereo
Computer Vision and Image Understanding
How Accurate Can Block Matches Be in Stereo Vision?
SIAM Journal on Imaging Sciences
Improving sub-pixel correspondence through upsampling
Computer Vision and Image Understanding
A new framework for 3D face reconstruction for self-occluded images
International Journal of Computational Vision and Robotics
Hi-index | 0.00 |
The invariance of the similarity measure in photometric distortions as well as its capability in producing sub-pixel accuracy are two desired and often required features in most stereo vision applications. In this paper we propose a new correlation-based measure which incorporates both mentioned requirements. Specifically, by using an appropriate interpolation scheme in the candidate windows of the matching image, and using the classical zero mean normalized cross correlation function, we introduce a suitable measure. Although the proposed measure is a non-linear function of the sub-pixel displacement parameter, its maximization results in a closed form solution, resulting in reduced complexity for its use in matching techniques. Application of the proposed measure in a number of benchmark stereo pair images reveals its superiority over existing correlation-based techniques used for sub-pixel accuracy.