M
Michal Havlena
Researcher at ETH Zurich
Publications - 39
Citations - 1338
Michal Havlena is an academic researcher from ETH Zurich. The author has contributed to research in topics: Structure from motion & 3D reconstruction. The author has an hindex of 17, co-authored 39 publications receiving 1125 citations. Previous affiliations of Michal Havlena include Czech Technical University in Prague & Oregon Health & Science University.
Papers
More filters
Proceedings ArticleDOI
Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition
TL;DR: An orthogonal strategy is explored, which uses all the 3D points and standard sampling, but performs feature matching implicitly, by quantization into a fine vocabulary, and achieves state-of-the-art performance, while the memory footprint is greatly reduced, since only visual word labels but no 3D point descriptors need to be stored.
Proceedings ArticleDOI
Large-Scale Location Recognition and the Geometric Burstiness Problem
TL;DR: It is shown that the implicit assumption that the number of inliers found by spatial verification can be used to distinguish between a related and an unrelated database photo with high precision does not hold for large datasets due to the appearance of geometric bursts.
Proceedings ArticleDOI
Predicting Matchability
TL;DR: In this article, the authors propose to filter out those points which would not survive the matching stage. But the best filtering criterion is not the response of the interest point detector, which is not surprising: the goal of detection are repeatable and well-localized points, whereas the objective of the selection are points whose descriptors can be matched successfully.
Book ChapterDOI
Efficient structure from motion by graph optimization
TL;DR: An efficient structure from motion algorithm that can deal with large image collections in a fraction of time and effort of previous approaches while providing comparable quality of the scene and camera reconstruction is presented.
Proceedings ArticleDOI
Learned Multi-patch Similarity
TL;DR: In this article, the authors propose to learn a matching function which directly maps multiple image patches to a scalar similarity score, which has advantages over methods based on pairwise patch similarity.