Combining geometric and appearance priors for robust homography estimation

Conference Article


European Conference on Computer Vision (ECCV)





Doc link


Download the digital copy of the doc pdf document


The homography between pairs of images are typically computed from the correspondence of keypoints, which are established by using image descriptors. When these descriptors are not reliable, either because of repetitive patterns or large amounts of clutter, additional priors need to be considered. The Blind PnP algorithm makes use of geometric priors to guide the search for matches while computing camera pose. Inspired by this, we propose a novel approach for homography estimation that combines geometric priors with appearance priors of ambiguous descriptors. More specifically, for each point we retain its best candidates according to appearance. We then prune the set of potential matches by iteratively shrinking the regions of the image that are consistent with the geometric prior. We can then successfully compute homographies between pairs of images containing highly repetitive patterns and even under oblique viewing conditions.


computer vision, object detection.

Author keywords

homography estimation, RANSAC

Scientific reference

E. Serradell, M. Özuysal, V. Lepetit, P. Fua and F. Moreno-Noguer. Combining geometric and appearance priors for robust homography estimation, 11th European Conference on Computer Vision, 2010, Crete, Greece, in Computer Vision - ECCV 2010, Vol 6313 of Lecture Notes in Computer Science, pp. 58-72, 2010, Springer, Berlin.