Related papers: D3Feat: Joint Learning of Dense Detection and Desc…

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many…

Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including…

Feature Descriptors and Detectors are two main components of feature-based point cloud registration. However, little attention has been drawn to the explicit representation of local and global semantics in the learning of descriptors and…

We present a novel differential matching algorithm for 3D point cloud registration. Instead of only optimizing the feature extractor for a matching algorithm, we propose a learning-based matching module optimized to the jointly-trained…

Change detection from traditional \added{2D} optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud \added{from photogrammetry or LiDAR surveying} can fill this…

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and…

Point cloud filtering, the main bottleneck of which is removing noise (outliers) while preserving geometric features, is a fundamental problem in 3D field. The two-step schemes involving normal estimation and position update have been shown…

Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet…

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…

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…

Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images. However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting…

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this…

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…

Geometry and topology constitute complementary descriptors of three-dimensional shape, yet existing benchmark datasets primarily capture geometric information while neglecting topological structure. This work addresses this limitation by…

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context.…

Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…

In this paper, we deal with the problem to predict the future 3D motions of 3D object scans from previous two consecutive frames. Previous methods mostly focus on sparse motion prediction in the form of skeletons. While in this paper we…

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However, creating feature representation of robust, discriminative…

To advance the state of the art in the creation of 3D foundation models, this paper introduces the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks and large-scale multi-view datasets. We propose a novel…

We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds. PPFNet learns local descriptors on pure geometry and is highly aware of…