We propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. With AWFT, we are able to extract meaningful intrinsic localized orientation-sensitive structures on surfaces, and use them in applications such as shape segmentation, salient point detection, feature point description, and matching. Our method outperforms previous approaches in the considered applications.
Melzi, S., Rodola, E., Castellani, U., Bronstein, M. (2016). Shape analysis with anisotropic windowed Fourier transform. In Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016 (pp.470-478). Institute of Electrical and Electronics Engineers Inc. [10.1109/3DV.2016.57].
Shape analysis with anisotropic windowed Fourier transform
Melzi, Simone;
2016
Abstract
We propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. With AWFT, we are able to extract meaningful intrinsic localized orientation-sensitive structures on surfaces, and use them in applications such as shape segmentation, salient point detection, feature point description, and matching. Our method outperforms previous approaches in the considered applications.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Rodola_Shape_2016.pdf
Solo gestori archivio
Dimensione
1.59 MB
Formato
Adobe PDF
|
1.59 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
