A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras
arXiv:2012.03683
Abstract
This paper reports on a novel nonparametric rigid point cloud registration framework that jointly integrates geometric and semantic measurements such as color or semantic labels into the alignment process and does not require explicit data association. The point clouds are represented as nonparametric functions in a reproducible kernel Hilbert space. The alignment problem is formulated as maximizing the inner product between two functions, essentially a sum of weighted kernels, each of which exploits the local geometric and semantic features. As a result of the continuous models, analytical gradients can be computed, and a local solution can be obtained by optimization over the rigid body transformation group. Besides, we present a new point cloud alignment metric that is intrinsic to the proposed framework and takes into account geometric and semantic information. The evaluations using publicly available stereo and RGB-D datasets show that the proposed method outperforms state-of-the-art outdoor and indoor frame-to-frame registration methods. An open-source GPU implementation is also provided.
arXiv comment8 pages, 5 figures
References in corpus (10)
- Categorical Reparameterization with Gumbel-Softmax
- Open3D: A Modern Library for 3D Data Processing
- 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
- Rigid and Articulated Point Registration with Expectation Conditional Maximization
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- Direct Sparse Odometry
- PCRNet: Point Cloud Registration Network using PointNet Encoding
- Nonparametric Continuous Sensor Registration
- Continuous Direct Sparse Visual Odometry from RGB-D Images
- Adaptive Continuous Visual Odometry from RGB-D Images