Related papers: Self-Supervised Learning of Part Mobility from Poi…

Implicit function based surface reconstruction has been studied for a long time to recover 3D shapes from point clouds sampled from surfaces. Recently, Signed Distance Functions (SDFs) and Occupany Functions are adopted in learning-based…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose a novel formulation that simultaneously learns a…

Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data. Despite recent progress, the self-supervised video prediction task is still challenging. One of the critical…

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is…

In this paper, we introduce a Point Recurrent Neural Network (PointRNN) for moving point cloud processing. At each time step, PointRNN takes point coordinates $\boldsymbol{P} \in \mathbb{R}^{n \times 3}$ and point features $\boldsymbol{X}…

A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually…

We consider the problem of segmenting objects in videos based on their motion and no other forms of supervision. Prior work has often approached this problem by using the principle of common fate, namely the fact that the motion of points…

In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike all existing methods which usually require a large amount of human annotations for full supervision, we propose the first unsupervised method,…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

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…

Point cloud, an efficient 3D object representation, has become popular with the development of depth sensing and 3D laser scanning techniques. It has attracted attention in various applications such as 3D tele-presence, navigation for…

Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet,…

In this paper, we propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape…

We propose a new approach to learn to segment multiple image objects without manual supervision. The method can extract objects form still images, but uses videos for supervision. While prior works have considered motion for segmentation, a…

We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. Distinct from most existing methods that focus on designing convolutional operators, our method designs a new learning…

3D single object tracking is a key issue for autonomous following robot, where the robot should robustly track and accurately localize the target for efficient following. In this paper, we propose a 3D tracking method called 3D-SiamRPN…

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia.…

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical…

Legged locomotion in constrained spaces (called crawl spaces) is challenging. In crawl spaces, current proprioceptive locomotion learning methods are difficult to achieve traverse because only ground features are inferred. In this study, a…