Related papers: DeepPoint3D: Learning Discriminative Local Descrip…

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…

Object retrieval and classification in point cloud data is challenged by noise, irregular sampling density and occlusion. To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high…

When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-life applications, we may be interested in learning new classes…

In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly…

We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use…

Retrieval in 3D point clouds is a challenging task that consists in retrieving the most similar point clouds to a given query within a reference of 3D points. Current methods focus on comparing descriptors of point clouds in order to…

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…

We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

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…

Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…

We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D…

We present a new point-based approach for modeling the appearance of real scenes. The approach uses a raw point cloud as the geometric representation of a scene, and augments each point with a learnable neural descriptor that encodes local…

Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven…

State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training have demonstrated potential in learning 3D representations by…

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance…

Robust data association is necessary for virtually every SLAM system and finding corresponding points is typically a preprocessing step for scan alignment algorithms. Traditionally, handcrafted feature descriptors were used for these…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

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.…

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation…