Rau, A;
Garcia-Hernando, G;
Stoyanov, D;
Brostow, GJ;
Turmukhambetov, D;
(2020)
Predicting Visual Overlap of Images Through Interpretable Non-metric Box Embeddings.
In:
Computer Vision – ECCV 2020.
(pp. pp. 629-646).
Springer Nature: Cham, Switzerland.
Preview |
Text
Rau_Predicting_Visual_Overlap_ECCV_2020.pdf - Published Version Download (6MB) | Preview |
Abstract
To what extent are two images picturing the same 3D surfaces? Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching and geometric verification of large sets of local features. This expense is further multiplied when a query image is evaluated against a gallery, e.g. in visual relocalization. While we don’t obviate the need for geometric verification, we propose an interpretable image-embedding that cuts the search in scale space to essentially a lookup. Our approach measures the asymmetric relation between two images. The model then learns a scene-specific measure of similarity, from training examples with known 3D visible-surface overlaps. The result is that we can quickly identify, for example, which test image is a close-up version of another, and by what scale factor. Subsequently, local features need only be detected at that scale. We validate our scene-specific model by showing how this embedding yields competitive image-matching results, while being simpler, faster, and also interpretable by humans.
Type: | Proceedings paper |
---|---|
Title: | Predicting Visual Overlap of Images Through Interpretable Non-metric Box Embeddings |
ISBN-13: | 978-3-030-58557-0 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1007/978-3-030-58558-7_37 |
Publisher version: | https://doi.org/10.1007/978-3-030-58558-7_37 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
Keywords: | Image embedding, Representation learning, Image localization, Interpretable representation |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10118960 |
Archive Staff Only
![]() |
View Item |