GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching

Simone Melzi, Riccardo Spezialetti, Federico Tombari, Michael M. Bronstein, Luigi Di Stefano, Emanuele Rodola; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4629-4638

Abstract


We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the local frame at each point; importantly, it directly inherits the properties and invariance classes of the underlying scalar function, making it remarkably robust under strong sampling artifacts, vertex noise, as well as non-rigid deformations. Existing local descriptors can directly benefit from our repeatable frames, as we showcase in a selection of 3D vision and shape analysis applications where we demonstrate state-of-the-art performance in a variety of challenging settings.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Melzi_2019_CVPR,
author = {Melzi, Simone and Spezialetti, Riccardo and Tombari, Federico and Bronstein, Michael M. and Stefano, Luigi Di and Rodola, Emanuele},
title = {GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}