Search Results - "Wandt, Bastian"

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation by Wandt, Bastian, Rosenhahn, Bodo

“…This paper addresses the problem of 3D human pose estimation from single images. While for a long time human skeletons were parameterized and fitted to the…”
Get full text

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection by Rudolph, Marco, Wehrbein, Tom, Rosenhahn, Bodo, Wandt, Bastian

“…In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect…”
Get full text

A graph-based approach can improve keypoint detection of complex poses: a proof-of-concept on injury occurrences in alpine ski racing by Zwölfer, Michael, Heinrich, Dieter, Wandt, Bastian, Rhodin, Helge, Spörri, Jörg, Nachbauer, Werner

“…For most applications, 2D keypoint detection works well and offers a simple and fast tool to analyse human movements. However, there remain many situations…”
Get full text

Deep learning-based 2D keypoint detection in alpine ski racing – A performance analysis of state-of-the-art algorithms applied to regular skiing and injury situations by Zwölfer, Michael, Heinrich, Dieter, Schindelwig, Kurt, Wandt, Bastian, Rhodin, Helge, Spörri, Jörg, Nachbauer, Werner

“…Objectives In this study, we examined the practicability of deep learning-based 2D keypoint detection applied to regular skiing and injury situations (i.e.,…”
Get full text

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows by Rudolph, Marco, Wandt, Bastian, Rosenhahn, Bodo

“…The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely…”
Get full text

DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion Models by Holmquist, Karl, Wandt, Bastian

“…Traditionally, monocular 3D human pose estimation employs a machine learning model to predict the most likely 3D pose for a given input image. However, a…”
Get full text

3D Reconstruction of Human Motion from Monocular Image Sequences by Wandt, Bastian, Ackermann, Hanno, Rosenhahn, Bodo

“…This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other…”
Get full text

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild by Wandt, Bastian, Rudolph, Marco, Zell, Petrissa, Rhodin, Helge, Rosenhahn, Bodo

“…Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved…”
Get full text

Asymmetric Student-Teacher Networks for Industrial Anomaly Detection by Rudolph, Marco, Wehrbein, Tom, Rosenhahn, Bodo, Wandt, Bastian

“…Industrial defect detection is commonly addressed with anomaly detection (AD) methods where no or only incomplete data of potentially occurring defects is…”
Get full text

Region-based Cycle-Consistent Data Augmentation for Object Detection by Kluger, Florian, Reinders, Christoph, Raetz, Kevin, Schelske, Philipp, Wandt, Bastian, Ackermann, Hanno, Rosenhahn, Bodo

“…Roads constitute a major part of the lives of everybody. Heavy use, for instance by cars and especially trucks, and even soil movement lead to visible damages…”
Get full text

The voraus-AD Dataset for Anomaly Detection in Robot Applications by Brockmann, Jan Thies, Rudolph, Marco, Rosenhahn, Bodo, Wandt, Bastian

“…During the operation of industrial robots, unusual events may endanger the safety of humans and the quality of production. When collecting data to detect such…”
Get full text

GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation by He, Xingzhe, Wandt, Bastian, Rhodin, Helge

“…Segmenting an image into its parts is a common pre-process for high-level vision tasks such as image editing. However, annotating masks for supervised training…”
Get full text

ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses by Wandt, Bastian, Little, James J., Rhodin, Helge

“…Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does…”
Get full text

AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation by Gholami, Mohsen, Wandt, Bastian, Rhodin, Helge, Ward, Rabab, Wang, Z. Jane

“…This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset…”
Get full text

Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows by Wehrbein, Tom, Rudolph, Marco, Rosenhahn, Bodo, Wandt, Bastian

“…3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore…”
Get full text

AudioViewer: Learning to Visualize Sounds by Song, Chunjin, Zhang, Yuchi, Peng, Willis, Mohaghegh, Parmis, Wandt, Bastian, Rhodin, Helge

“…A long-standing goal in the field of sensory substitution is enabling sound perception for deaf and hard of hearing (DHH) people by visualizing audio content…”
Get full text

DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models by Holmquist, Karl, Wandt, Bastian

“…Traditionally, monocular 3D human pose estimation employs a machine learning model to predict the most likely 3D pose for a given input image. However, a…”
Get full text

LatentKeypointGAN: Controlling Images via Latent Keypoints by He, Xingzhe, Wandt, Bastian, Rhodin, Helge

“…Conference on Robots and Vision 2023 Generative adversarial networks (GANs) have attained photo-realistic quality in image generation. However, how to best…”
Get full text

Temporally-consistent 3D Reconstruction of Birds by Hägerlind, Johannes, Hentati-Sundberg, Jonas, Wandt, Bastian

“…This paper deals with 3D reconstruction of seabirds which recently came into focus of environmental scientists as valuable bio-indicators for environmental…”
Get full text

Pose Modulated Avatars from Video by Song, Chunjin, Wandt, Bastian, Rhodin, Helge

“…It is now possible to reconstruct dynamic human motion and shape from a sparse set of cameras using Neural Radiance Fields (NeRF) driven by an underlying…”
Get full text