Efficient image retrieval for 3D structures

Large scale image retrieval systems for speci c objects generally employ visual words together with a ranking based on a geometric relation between the query and target images. Previous work has used planar homographies for this geometric relation. Here we replace the planar transformation by epipolar geometry in order to improve the retrieval performance for 3D structures. To this end, we introduce a new minimal solution for computing the af ne fundamental matrix. The solution requires only two corresponding elliptical regions. Unlike previous approaches it does not require the rotation of the image patches, and ensures that the necessary epipolar tangency constraints are satis ed. The solution is well suited for real time reranking in large scale image retrieval, since (i) elliptical correspondences are readily available from the af ne region detections, and (ii) the use of only two region correspondences is very ef cient in a RANSAC framework where the number of samples required grows exponentially with sample size. We demonstrate a gain in computational ef ciency (over other methods of solution) without a loss in quality of the estimated epipolar geometry. We present a quantitative performance evaluation on the Oxford and Paris image retrieval benchmarks, and demonstrate that retrieval of 3D structures is indeed improved.