Estimating Low-Rank Region Likelihood Maps
| Autor: | Zoltan Kato, Gabriela Csurka, Andor Juhasz, Martin Humenberger |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Current (mathematics)
Rank (linear algebra) business.industry Computer science Plane (geometry) 020207 software engineering Pattern recognition 02 engineering and technology Image (mathematics) Feature (computer vision) 0202 electrical engineering electronic engineering information engineering Homography 020201 artificial intelligence & image processing Artificial intelligence business Baseline (configuration management) Sparse matrix Homography (computer vision) |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.01379 |
| Popis: | Low-rank regions capture geometrically meaningful structures in an image which encompass typical local features such as edges, corners and all kinds of regular, symmetric, often repetitive patterns, that are commonly found in man-made environment. While such patterns are challenging current state-of-the-art feature correspondence methods, the recovered homography of a low-rank texture readily provides 3D structure with respect to a 3D plane, without any prior knowledge of the visual information on that plane. However, the automatic and efficient detection of the broad class of low-rank regions is unsolved. Herein, we propose a novel self-supervised low-rank region detection deep network that predicts a low-rank likelihood map from an image. The evaluation of our method on real-world datasets shows not only that it reliably predicts low-rank regions in the image similarly to our baseline method, but thanks to the data augmentations used in the training phase it generalizes well to difficult cases (e.g. day/night lighting, low contrast, underexposure) where the baseline prediction fails. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|