Related papers: Addressing the Sim2Real Gap in Robotic 3D Object C…

6D object pose estimation problem has been extensively studied in the field of Computer Vision and Robotics. It has wide range of applications such as robot manipulation, augmented reality, and 3D scene understanding. With the advent of…

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. However, discrepancies with the real data acquired from various…

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…

The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to…

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the…

To aid humans in everyday tasks, robots need to know which objects exist in the scene, where they are, and how to grasp and manipulate them in different situations. Therefore, object recognition and grasping are two key functionalities for…

3D softwares are now capable of producing highly realistic images that look nearly indistinguishable from the real images. This raises the question: can real datasets be enhanced with 3D rendered data? We investigate this question. In this…

We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented…

Robots that assist humans in their daily lives should be able to locate specific instances of objects in an environment that match a user's desired objects. This task is known as instance-specific image goal navigation (InstanceImageNav),…

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore,…

Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object reconstruction require explicitly defined physical constraints…

This paper addresses the problem of simultaneous 3D reconstruction and material recognition and segmentation. Enabling robots to recognise different materials (concrete, metal etc.) in a scene is important for many tasks, e.g. robotic…

Synthetic visual data can provide practically infinite diversity and rich labels, while avoiding ethical issues with privacy and bias. However, for many tasks, current models trained on synthetic data generalize poorly to real data. The…

Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning…

Scene Classification has been addressed with numerous techniques in computer vision literature. However, with the increasing number of scene classes in datasets in the field, it has become difficult to achieve high accuracy in the context…

Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors…

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to "adapt" a model trained on simulated images so that it performs well on…

This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The…

Graph matching aims to establish correspondences between vertices of graphs such that both the node and edge attributes agree. Various learning-based methods were recently proposed for finding correspondences between image key points based…