Related papers: DGCM-Net: Dense Geometrical Correspondence Matchin…

Robotic grasping of 3D deformable objects is critical for real-world applications such as food handling and robotic surgery. Unlike rigid and articulated objects, 3D deformable objects have infinite degrees of freedom. Fully defining their…

Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn…

We present the Grasp Proposal Network (GP-net), a Convolutional Neural Network model which can generate 6-DoF grasps from flexible viewpoints, e.g. as experienced by mobile manipulators. To train GP-net, we synthetically generate a dataset…

Motivated by the astonishing capabilities of natural intelligent agents and inspired by theories from psychology, this paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment.…

In this paper, we address the problem of learning 3D human pose and body shape from 2D image dataset, without having to use 3D dataset (body shape and pose). The idea is to use dense correspondences between image points and a body surface,…

We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene…

Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can…

We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our…

Transparent objects are common in our daily life and frequently handled in the automated production line. Robust vision-based robotic grasping and manipulation for these objects would be beneficial for automation. However, the majority of…

The ability to successfully grasp objects is crucial in robotics, as it enables several interactive downstream applications. To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set…

Grasping in dynamic environments presents a unique set of challenges. A stable and reachable grasp can become unreachable and unstable as the target object moves, motion planning needs to be adaptive and in real time, the delay in…

Grasping objects is one of the most important abilities that a robot needs to master in order to interact with its environment. Current state-of-the-art methods rely on deep neural networks trained to jointly predict a graspability score…

Human ability of both versatile grasping of given objects and grasping of novel (as of yet unseen) objects is truly remarkable. This probably arises from the experience infants gather by actively playing around with diverse objects.…

Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive…

Finding corresponding pixels within a pair of images is a fundamental computer vision task with various applications. Due to the specific requirements of different tasks like optical flow estimation and local feature matching, previous…

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine…

We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of…

In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object. Our method relies on a Graph Neural Network…

Land cover classification of remote sensing images is a challenging task due to limited amounts of annotated data, highly imbalanced classes, frequent incorrect pixel-level annotations, and an inherent complexity in the semantic…

Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling…