Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised learning tasks on point clouds such as classification and …

In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds
generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class …

Developments in the field of artificial intelligence have made great strides in the field of
automatic semantic segmentation, both in the 2D (image) and 3D spaces. Within the context …

Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised semantic learning tasks on point clouds such as classification …

Semantic 3D scene understanding is a fundamental problem in computer vision and
robotics. Despite recent advances in deep learning, its application to multi-domain 3D …

Pose estimation of deformable objects is a fundamental and challenging problem in
robotics. We present a novel solution to this problem by first reconstructing a 3D model of the …

3-D shape reconstruction is essential in the navigation of minimally invasive and auto robot-
guided surgeries whose operating environments are indirect and narrow, and there have …

Traditional graph-based semi-supervised learning (SSL) approaches are not suited for
massive data and large label scenarios since they scale linearly with the number of edges …

Object segmentation in three-dimensional (3-D) point clouds is a critical task for robots
capable of 3-D perception. Despite the impressive performance of deep learning-based …

Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D
scene data. Such data, if completely and well annotated, can serve as useful ingredients for …