Abstract : Reflective symmetry can be used as a strong prior for many computer vision tasks. We interpret the planar reflective symmetry detection by using the property of an involution, which implies that two pairs of matched points are enough to define a planar reflective symmetry observed from a non-frontal viewpoint. This makes the reflective symmetry estimation as efficient as the classical homography estimation in binocular stereovision. This simple reflective symmetry computation can be plugged into any multiple model estimation to detect multiple symmetries at different scales and locations in images. The experimental results show that the proposed method is able to detect single and multiple reflective symmetries both in frontal and non fronto-parallel viewpoints.
https://hal-enpc.archives-ouvertes.fr/hal-01179500
Contributeur : Pascal Monasse
<>
Soumis le : lundi 23 avril 2018 - 09:33:15
Dernière modification le : lundi 25 février 2019 - 14:40:27
Document(s) archivé(s) le : mercredi 19 septembre 2018 - 00:01:22
Zhongwei Tang, Pascal Monasse, Jean-Michel Morel. Reflexive Symmetry Detection in Single Image. Curves and Surfaces, Jun 2014, Paris, France. pp.452-460, ⟨10.1007/978-3-319-22804-4_31⟩. ⟨hal-01179500v2⟩
