SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Authors:
Top Cited Papers
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11748-11757
Abstract
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neither general nor representative. In this paper, we introduce a new, yet conceptually simple, neural architecture, termed SpinNet, to extract local features which are rotationally invariant whilst sufficiently informative to enable accurate registration. A Spatial Point Transformer is first introduced to map the input local surface into a carefully designed cylindrical space, enabling end-to-end optimization with SO(2) equivariant representation. A Neural Feature Extractor which leverages the powerful point-based and 3D cylindrical convolutional neural layers is then utilized to derive a compact and representative descriptor for matching. Extensive experiments on both indoor and outdoor datasets demonstrate that SpinNet outperforms existing state-of-the-art techniques by a large margin. More critically, it has the best generalization ability across unseen scenarios with different sensor modalities. The code is available at https://github.com/QingyongHu/SpinNet.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
This publication has 52 references indexed in Scilit:
- Shape2PoseACM Transactions on Graphics, 2014
- 3D Object Recognition in Cluttered Scenes with Local Surface Features: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Rotational Projection Statistics for 3D Local Surface Description and Object RecognitionInternational Journal of Computer Vision, 2013
- Challenging data sets for point cloud registration algorithmsThe International Journal of Robotics Research, 2012
- On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered ScenesInternational Journal of Computer Vision, 2009
- Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images2008
- 3D free-form object recognition in range images using local surface patchesPattern Recognition Letters, 2007
- Recognizing Objects in Range Data Using Regional Point Descriptors2004
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Structural indexing: efficient 2D object recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992