Deep learning has recently gained popularity achieving state-of-the-art performance in tasks
involving text, sound, or image processing. Due to its outstanding performance, there have …

With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual
(RGB) sensing has become available for widespread use. The complementary nature of the …

This paper studies the unsupervised embedding learning problem, which requires an
effective similarity measurement between samples in low-dimensional embedding space …

A deep learning architecture is proposed to predict graspable locations for robotic
manipulation. It considers situations where no, one, or multiple object (s) are seen. By …

Paired RGB and depth images are becoming popular multi-modal data adopted in computer
vision tasks. Traditional methods based on Convolutional Neural Networks (CNNs) typically …

We focus on the task of amodal 3D object detection in RGB-D images, which aims to
produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep …

In this paper we study the problem of object detection for RGB-D images using semantically
rich image and depth features. We propose a new geocentric embedding for depth images …

Current methods for training convolutional neural networks depend on large amounts of
labeled samples for supervised training. In this paper we present an approach for training a …

Abstract We propose a Convolutional Neural Network (CNN)-based model``RotationNet,''
which takes multi-view images of an object as input and jointly estimates its pose and object …

In recent years, the task of estimating the 6D pose of object instances and complete scenes,
ie camera localization, from a single input image has received considerable attention …