Journal
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
Volume -, Issue -, Pages 8957-8965Publisher
IEEE
DOI: 10.1109/ICCV.2019.00905
Keywords
-
Ask authors/readers for more resources
Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking. State-of-the-art methods require computing low-level features as input or extracting patch-based features with limited receptive field. In this work, we present fully-convolutional geometric features, computed in a single pass by a 3D fully-convolutional network. We also present new metric learning losses that dramatically improve performance. Fully-convolutional geometric features are compact, capture broad spatial context, and scale to large scenes. We experimentally validate our approach on both indoor and outdoor datasets. Fully-convolutional geometric features achieve state-of-the-art accuracy without requiring prepossessing, are compact (32 dimensions), and are 290 times faster than the most accurate prior method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available