UPDesc: Unsupervised Point Descriptor Learning for Robust Registration
- URL: http://arxiv.org/abs/2108.02740v1
- Date: Thu, 5 Aug 2021 17:11:08 GMT
- Title: UPDesc: Unsupervised Point Descriptor Learning for Robust Registration
- Authors: Lei Li, Hongbo Fu, Maks Ovsjanikov
- Abstract summary: UPDesc is an unsupervised method to learn point descriptors for robust point cloud registration.
We show that our learned descriptors yield superior performance over existing unsupervised methods.
- Score: 54.95201961399334
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this work, we propose UPDesc, an unsupervised method to learn point
descriptors for robust point cloud registration. Our work builds upon a recent
supervised 3D CNN-based descriptor extraction framework, namely, 3DSmoothNet,
which leverages a voxel-based representation to parameterize the surrounding
geometry of interest points. Instead of using a predefined fixed-size local
support in voxelization, which potentially limits the access of richer local
geometry information, we propose to learn the support size in a data-driven
manner. To this end, we design a differentiable voxelization module that can
back-propagate gradients to the support size optimization. To optimize
descriptor similarity, the prior 3D CNN work and other supervised methods
require abundant correspondence labels or pose annotations of point clouds for
crafting metric learning losses. Differently, we show that unsupervised
learning of descriptor similarity can be achieved by performing geometric
registration in networks. Our learning objectives consider descriptor
similarity both across and within point clouds without supervision. Through
extensive experiments on point cloud registration benchmarks, we show that our
learned descriptors yield superior performance over existing unsupervised
methods.
Related papers
- DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
We present a novel learning-based alignment network for complex alignment scenes.
We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
arXiv Detail & Related papers (2021-11-15T08:27:21Z) - Point Discriminative Learning for Unsupervised Representation Learning
on 3D Point Clouds [54.31515001741987]
We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds.
We achieve this by imposing a novel point discrimination loss on the middle level and global level point features.
Our method learns powerful representations and achieves new state-of-the-art performance.
arXiv Detail & Related papers (2021-08-04T15:11:48Z) - Point Cloud Registration using Representative Overlapping Points [10.843159482657303]
We propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration.
Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score.
Experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods.
arXiv Detail & Related papers (2021-07-06T12:52:22Z) - Robust Kernel-based Feature Representation for 3D Point Cloud Analysis
via Circular Graph Convolutional Network [2.42919716430661]
We present a new local feature description method that is robust to rotation, density, and scale variations.
To improve representations of the local descriptors, we propose a global aggregation method.
Our method shows superior performances when compared to the state-of-the-art methods.
arXiv Detail & Related papers (2020-12-22T18:02:57Z) - Unsupervised Feedforward Feature (UFF) Learning for Point Cloud
Classification and Segmentation [57.62713515497585]
Unsupervised feedforward feature learning is proposed for joint classification and segmentation of 3D point clouds.
The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner.
It learns global shape features through the encoder and local point features through the encoder-decoder architecture.
arXiv Detail & Related papers (2020-09-02T18:25:25Z) - SoftPoolNet: Shape Descriptor for Point Cloud Completion and
Classification [93.54286830844134]
We propose a method for 3D object completion and classification based on point clouds.
For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy.
We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
arXiv Detail & Related papers (2020-08-17T14:32:35Z) - DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF
Relocalization [56.15308829924527]
We propose a Siamese network that jointly learns 3D local feature detection and description directly from raw 3D points.
For detecting 3D keypoints we predict the discriminativeness of the local descriptors in an unsupervised manner.
Experiments on various benchmarks demonstrate that our method achieves competitive results for both global point cloud retrieval and local point cloud registration.
arXiv Detail & Related papers (2020-07-17T20:21:22Z) - Unsupervised Learning of 3D Point Set Registration [15.900382629390297]
Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.
This paper proposes Deep-3DAligner, a novel unsupervised registration framework based on a newly introduced deep Spatial Correlation Representation (SCR) feature.
Our method starts with optimizing a randomly latent SCR feature, which is then decoded to a geometric transformation to align source and target point sets.
arXiv Detail & Related papers (2020-06-11T05:21:38Z) - End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds [67.27510166559563]
We propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds.
Our method outperforms existing local descriptors both quantitatively and qualitatively.
arXiv Detail & Related papers (2020-03-12T15:41:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.