Related papers: Self-Supervised Feature Learning from Partial Poin…

In recent years, with the development of computing resources and LiDAR, point cloud semantic segmentation has attracted many researchers. For the sparsity of point clouds, although there is already a way to deal with sparse convolution,…

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning.…

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…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Most of the existing self-supervised feature learning methods for 3D data either learn 3D features from point cloud data or from multi-view images. By exploring the inherent multi-modality attributes of 3D objects, in this paper, we propose…

We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks…

In this work, we tackle the challenging problem of category-level object pose and size estimation from a single depth image. Although previous fully-supervised works have demonstrated promising performance, collecting ground-truth pose…

3D building models with facade details are playing an important role in many applications now. Classifying point clouds at facade-level is key to create such digital replicas of the real world. However, few studies have focused on such…

Recognizing human actions from point cloud videos has attracted tremendous attention from both academia and industry due to its wide applications like automatic driving, robotics, and so on. However, current methods for point cloud action…

In 2D image processing, some attempts decompose images into high and low frequency components for describing edge and smooth parts respectively. Similarly, the contour and flat area of 3D objects, such as the boundary and seat area of a…

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…

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

We propose a new representation of visual data that disentangles object position from appearance. Our method, termed Deep Latent Particles (DLP), decomposes the visual input into low-dimensional latent ``particles'', where each particle is…

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…

During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and…

LiDAR is widely used to capture accurate 3D outdoor scene structures. However, LiDAR produces many undesirable noise points in snowy weather, which hamper analyzing meaningful 3D scene structures. Semantic segmentation with snow labels…

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,…

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…

In computer-aided design (CAD) community, the point cloud data is pervasively applied in reverse engineering, where the point cloud analysis plays an important role. While a large number of supervised learning methods have been proposed to…