Related papers: LRGNet: Learnable Region Growing for Class-Agnosti…

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so…

Autonomous driving is a safety-critical application, and it is therefore a top priority that the accompanying assistance systems are able to provide precise information about the surrounding environment of the vehicle. Tasks such as 3D…

We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral…

We propose a method for instance-level segmentation that uses RGB-D data as input and provides detailed information about the location, geometry and number of individual objects in the scene. This level of understanding is fundamental for…

In the field of SLAM (Simultaneous Localization And Mapping) for robot navigation, mapping the environment is an important task. In this regard the Lidar sensor can produce near accurate 3D map of the environment in the format of point…

Recent advances in point cloud perception have demonstrated remarkable progress in scene understanding through vision-language alignment leveraging large language models (LLMs). However, existing methods may still encounter challenges in…

Airborne topographic LiDAR is an active remote sensing technology that emits near-infrared light to map objects on the Earth's surface. Derived products of LiDAR are suitable to service a wide range of applications because of their rich…

Three-dimensional (3D) point cloud analysis has become one of the attractive subjects in realistic imaging and machine visions due to its simplicity, flexibility and powerful capacity of visualization. Actually, the representation of scenes…

Novel class discovery (NCD) for semantic segmentation is the task of learning a model that can segment unlabelled (novel) classes using only the supervision from labelled (base) classes. This problem has recently been pioneered for 2D image…

Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges…

Real-time 3D object detection from point clouds is essential for dynamic scene understanding in applications such as augmented reality, robotics and navigation. We introduce a novel Spatial-prioritized and Rank-aware 3D object detection…

3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware…

In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph. We design a graph neural network, named Point-GNN,…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the…

Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based…

Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing…

Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically…

The visual system of a robot has different requirements depending on the application: it may require high accuracy or reliability, be constrained by limited resources or need fast adaptation to dynamically changing environments. In this…

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large…