Markus Oberweger
YOU?
Author Swipe
View article: Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations
Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations Open
We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images…
View article: HOnnotate: A Method for 3D Annotation of Hand and Object Poses
HOnnotate: A Method for 3D Annotation of Hand and Object Poses Open
We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images fo…
View article: Honnotate: A method for 3D annotation of hand and object pose
Honnotate: A method for 3D annotation of hand and object pose Open
International audience
View article: HO-3D: A Multi-User, Multi-Object Dataset for Joint 3D Hand-Object Pose Estimation.
HO-3D: A Multi-User, Multi-Object Dataset for Joint 3D Hand-Object Pose Estimation. Open
We propose a new dataset for 3D hand+object pose estimation from color images, together with a method for efficiently annotating this dataset, and a 3D pose prediction method based on this dataset. The current lack of training data makes t…
View article: HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images Open
We propose an automatic method for generating high-quality annotations for depth-based hand segmentation, and introduce a large-scale hand segmentation dataset. Existing datasets are typically limited to a single hand. By exploiting the vi…
View article: Generalized Feedback Loop for Joint Hand-Object Pose Estimation
Generalized Feedback Loop for Joint Hand-Object Pose Estimation Open
We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by …
View article: Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations
Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations Open
We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images…
View article: Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation
Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation Open
International audience
View article: Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images Open
International audience
View article: Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images Open
We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy…
View article: HandSeg: An Automatically Labeled Dataset for Hand Segmentation from\n Depth Images
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from\n Depth Images Open
We propose an automatic method for generating high-quality annotations for\ndepth-based hand segmentation, and introduce a large-scale hand segmentation\ndataset. Existing datasets are typically limited to a single hand. By\nexploiting the…
View article: HandSeg: A Dataset for Hand Segmentation from Depth Images.
HandSeg: A Dataset for Hand Segmentation from Depth Images. Open
We introduce a large-scale RGBD hand segmentation dataset, with detailed and automatically generated high-quality ground-truth annotations. Existing real-world datasets are limited in quantity due to the difficulty in manually annotating g…
View article: DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation Open
DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works. Here we show that with simple i…
View article: Training a Feedback Loop for Hand Pose Estimation
Training a Feedback Loop for Hand Pose Estimation Open
We propose an entirely data-driven approach to estimating the 3D pose of a hand given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a f…
View article: Efficiently Creating 3D Training Data for Fine Hand Pose Estimation
Efficiently Creating 3D Training Data for Fine Hand Pose Estimation Open
While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far. As a result, existing datasets are limited to a few …