Details

Autor(en) / Beteiligte

• Khoury, Marc
• Qian-Yi Zhou
• Koltun, Vladlen

Titel

Learning Compact Geometric Features

Ist Teil von

• 2017 IEEE International Conference on Computer Vision (ICCV), 2017, p.153-161

Ort / Verlag

IEEE

Erscheinungsjahr

2017

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D vision. Current state-of-the-art local features for unstructured point clouds have been manually crafted and none combines the desirable properties of precision, compactness, and robustness. We show that features with these properties can be learned from data, by optimizing deep networks that map high-dimensional histograms into low-dimensional Euclidean spaces. The presented approach yields a family of features, parameterized by dimension, that are both more compact and more accurate than existing descriptors.