Related papers: Density-invariant Features for Distant Point Cloud…

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the…

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…

Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective…

Point cloud registration is a classical topic in the field of 3D Vision and Computer Graphics. Generally, the implementation of registration is typically sensitive to similarity transformations (translation, scaling, and rotation), noisy…

In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to combine the advantages of inter-instance…

High-dimensional and complex spectral structures make the clustering of hyperspectral images (HSI) a challenging task. Subspace clustering is an effective approach for addressing this problem. However, current subspace clustering algorithms…

3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense.…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Existing LiDAR semantic segmentation models often suffer from decreased accuracy when exposed to adverse weather conditions. Recent methods addressing this issue focus on enhancing training data through weather simulation or universal…

We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with…

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature…

Incomplete multi-view clustering (IMVC) is an unsupervised approach, among which IMVC via contrastive learning has received attention due to its excellent performance. The previous methods have the following problems: 1) Over-reliance on…

While deep neural networks have made remarkable progress in various vision tasks, their performance typically deteriorates when tested in out-of-distribution (OOD) scenarios. Many OOD methods focus on extracting domain-invariant features…

We describe a novel approach to indoor place recognition from RGB point clouds based on aggregating low-level colour and geometry features with high-level implicit semantic features. It uses a 2-stage deep learning framework, in which the…

Point cloud registration is crucial for ensuring 3D alignment consistency of multiple local point clouds in 3D reconstruction for remote sensing or digital heritage. While various point cloud-based registration methods exist, both…

When classifying point clouds, a large amount of time is devoted to the process of engineering a reliable set of features which are then passed to a classifier of choice. Generally, such features - usually derived from the 3D-covariance…

With the development of numerous 3D sensing technologies, object registration on cross-source point cloud has aroused researchers' interests. When the point clouds are captured from different kinds of sensors, there are large and different…

Designing a registration framework for images that do not share the same probability distribution is a major challenge in modern image analytics yet trivial task for the human visual system (HVS). Discrepancies in probability distributions,…

LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention)…

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn…