Related papers: Sonata: Self-Supervised Learning of Reliable Point…
Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…
Point cloud data has been extensively studied due to its compact form and flexibility in representing complex 3D structures. The ability of point cloud data to accurately capture and represent intricate 3D geometry makes it an ideal choice…
Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept…
Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised…
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…
Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods…
Recent advances in computer vision and deep learning have shown promising performance in estimating rigid/similarity transformation between unregistered point clouds of complex objects and scenes. However, their performances are mostly…
Recent progress of semantic point clouds analysis is largely driven by synthetic data (e.g., the ModelNet and the ShapeNet), which are typically complete, well-aligned and noisy free. Therefore, representations of those ideal synthetic…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part…
Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annotation difficulty. As…
With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…
Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less…
Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach. However, it remains open whether such a framework generalizes to the unique challenges…
Semantic understanding of 3D point clouds is important for various robotics applications. Given that point-wise semantic annotation is expensive, in this paper, we address the challenge of learning models with extremely sparse labels. The…
Self-supervised learning (SSL) on 3D point clouds has the potential to learn feature representations that can transfer to diverse sensors and multiple downstream perception tasks. However, recent SSL approaches fail to define pretext tasks…
Large and rich data is a prerequisite for effective training of deep neural networks. However, the irregularity of point cloud data makes manual annotation time-consuming and laborious. Self-supervised representation learning, which…
Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely accessible, acquiring 3D assets requires specialized expertise or…
Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data…