EasyFlow: increasing the convergence basin of variational image matching with a feature-based cost
| Autor: | Adrien Bartoli, Mohamed Tamaazousti, Romain Dupont, Jim Braux-Zin |
|---|---|
| Přispěvatelé: | Laboratoire d'Informatique, de Modélisation et d'optimisation des Systèmes (LIMOS), SIGMA Clermont (SIGMA Clermont)-Université d'Auvergne - Clermont-Ferrand I (UdA)-Ecole Nationale Supérieure des Mines de St Etienne-Centre National de la Recherche Scientifique (CNRS)-Université Blaise Pascal - Clermont-Ferrand 2 (UBP), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Institut Pascal (IP), SIGMA Clermont (SIGMA Clermont)-Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne [2017-2020] (UCA [2017-2020]), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-Université d'Auvergne - Clermont-Ferrand I (UdA)-SIGMA Clermont (SIGMA Clermont)-Ecole Nationale Supérieure des Mines de St Etienne (ENSM ST-ETIENNE)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), SIGMA Clermont (SIGMA Clermont)-Université Clermont Auvergne [2017-2020] (UCA [2017-2020])-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Matching (graph theory)
business.industry [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Optical flow 02 engineering and technology Modular design Maxima and minima Motion field Feature (computer vision) Computer Science::Computer Vision and Pattern Recognition Motion estimation Convergence (routing) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Computer Vision and Pattern Recognition Artificial intelligence business Software ComputingMilieux_MISCELLANEOUS Mathematics |
| Zdroj: | IET Computer Vision IET Computer Vision, IET, 2017, 11 (2), pp.122-134. ⟨10.1049/iet-cvi.2016.0090⟩ IET Computer Vision, 2017, 11 (2), pp.122-134. ⟨10.1049/iet-cvi.2016.0090⟩ |
| ISSN: | 1751-9632 1751-9640 |
| DOI: | 10.1049/iet-cvi.2016.0090⟩ |
| Popis: | Dense motion field estimation is a key computer vision problem. Many solutions have been proposed to compute small or large displacements, narrow or wide baseline stereo disparity, or non-rigid surface registration, but a unified methodology is still lacking. The authors introduce a general framework that robustly combines direct and feature-based matching. The feature-based cost is built around a novel robust distance function that handles keypoints and weak features such as segments. It allows us to use putative feature matches to guide dense motion estimation out of local minima. The authors’ framework uses a robust direct data term. It is implemented with a powerful second-order regularisation with external and self-occlusion reasoning. Their framework achieves state-of-the-art performance in several cases (standard optical flow benchmarks, wide-baseline stereo and non-rigid surface registration). Their framework has a modular design that customises to specific application needs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text