Modeling hand-object manipulations is essential for understanding how humans interact with their environment. Recent efforts to recover 3D information from RGB images have been directed towards fully-supervised methods which require large amounts of labeled training samples. However, collecting 3D ground-truth data for hand-object interactions is costly, tedious, and error-prone. In this thesis, we propose several contributions to overcome this challenge.First, we propose a fully automatic method to generate synthetic data with hand-object interactions for training. We generate ObMan, a synthetic dataset with automatically generated labels, and use it to train a deep convolutional neural network to reconstruct the observed object and the ha...
We study how well different types of approaches generalise in the task of 3D hand pose estimation un...
3D object detection and pose estimation are of primary importance for tasks such as robotic manipula...
Schröder M, Ritter H. Hand-Object Interaction Detection with Fully Convolutional Networks. In: The ...
Modeling hand-object manipulations is essential for understanding how humans interact with their env...
International audienceModeling hand-object manipulations is essential for understanding how humans i...
Project website: https://hassony2.github.io/homan.htmlInternational audienceOur work aims to obtain ...
International audienceEstimating hand-object manipulations is essential for interpreting and imitati...
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even ...
We present a pipeline able to extract 3D real-world measurements from RGB-D images with high accurac...
International audienceWe analyze functional manipulations of handheld objects, formalizing the probl...
As virtual and augmented reality (VR/AR) technology gains popularity, facilitating intuitive digital...
We study the problem of 3D hand shape and pose estimation from monocular RGB images. Recent studies ...
Digital human characters are a mainstay of video games, film, and interactive computer graphics appl...
In this work we study the use of 3D hand poses to recognize first-person dynamic hand actions intera...
Mastering robotic grasping is a necessary skill for a robot to perform tasks involving the manipulat...
We study how well different types of approaches generalise in the task of 3D hand pose estimation un...
3D object detection and pose estimation are of primary importance for tasks such as robotic manipula...
Schröder M, Ritter H. Hand-Object Interaction Detection with Fully Convolutional Networks. In: The ...
Modeling hand-object manipulations is essential for understanding how humans interact with their env...
International audienceModeling hand-object manipulations is essential for understanding how humans i...
Project website: https://hassony2.github.io/homan.htmlInternational audienceOur work aims to obtain ...
International audienceEstimating hand-object manipulations is essential for interpreting and imitati...
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even ...
We present a pipeline able to extract 3D real-world measurements from RGB-D images with high accurac...
International audienceWe analyze functional manipulations of handheld objects, formalizing the probl...
As virtual and augmented reality (VR/AR) technology gains popularity, facilitating intuitive digital...
We study the problem of 3D hand shape and pose estimation from monocular RGB images. Recent studies ...
Digital human characters are a mainstay of video games, film, and interactive computer graphics appl...
In this work we study the use of 3D hand poses to recognize first-person dynamic hand actions intera...
Mastering robotic grasping is a necessary skill for a robot to perform tasks involving the manipulat...
We study how well different types of approaches generalise in the task of 3D hand pose estimation un...
3D object detection and pose estimation are of primary importance for tasks such as robotic manipula...
Schröder M, Ritter H. Hand-Object Interaction Detection with Fully Convolutional Networks. In: The ...