12 citations · 16 across the 5 of their papers we have counts for
6 papers
Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture
Tom Wehrbein, Bodo Rosenhahn
State-of-the-art methods can recover accurate overall 3D human body motion from in-the-wild videos. However, they often fail to capture fine-grained articulations, especially in th…
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn +1
Monocular 3D human pose and shape estimation is an inherently ill-posed problem due to depth ambiguities, occlusions, and truncations. Recent probabilistic approaches learn a distr…
Personalized 3D Human Pose and Shape Refinement
Tom Wehrbein, Bodo Rosenhahn, Iain Matthews +1
Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predi…
Asymmetric Student-Teacher Networks for Industrial Anomaly Detection
Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn +1
Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is available. This work disc…
Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection
Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn +1
In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect detection without req…
Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn +1
3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these ambiguities and…