Related papers: PRNet: Self-Supervised Learning for Partial-to-Par…
This work considers a new task in geometric deep learning: generating a triangulation among a set of points in 3D space. We present PointTriNet, a differentiable and scalable approach enabling point set triangulation as a layer in 3D…
Point cloud registration is an important task in robotics and autonomous driving to estimate the ego-motion of the vehicle. Recent advances following the coarse-to-fine manner show promising potential in point cloud registration. However,…
In this work, we propose a self-supervised learning method for affine image registration on 3D medical images. Unlike optimisation-based methods, our affine image registration network (AIRNet) is designed to directly estimate the…
Object point cloud classification has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet. These benchmarks assume point clouds covering complete surfaces of object instances, for…
Registering urban point clouds is a quite challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data. In this paper, we propose SARNet, a novel semantic augmented registration network aimed at achieving…
We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…
Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on non-Euclidean domains is still a very active area of…
In feature-learning based point cloud registration, the correct correspondence construction is vital for the subsequent transformation estimation. However, it is still a challenge to extract discriminative features from point cloud,…
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making…
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in…
We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point…
Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient…
Previous works have shown that face recognition with high accurate 3D data is more reliable and insensitive to pose and illumination variations. Recently, low-cost and portable 3D acquisition techniques like ToF(Time of Flight) and DoE…
As a fundamental problem in computer vision, point cloud registration aims to seek the optimal transformation for aligning a pair of point clouds. In most existing methods, the information flows are usually forward transferring, thus…
Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point…
Much progress has been made on the task of learning-based 3D point cloud registration, with existing methods yielding outstanding results on standard benchmarks, such as ModelNet40, even in the partial-to-partial matching scenario.…
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points…
LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mechanisms, spatial…
Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving. Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them. However,…
Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…