2 citations · 7 across the 17 of their papers we have counts for
18 papers
Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation
Daniel Kienzle, Katja Ludwig, Julian Lorenz +2
Obtaining the precise 3D motion of a table tennis ball from standard monocular videos is a challenging problem, as existing methods trained on synthetic data struggle to generalize…
MMMS: Multi-Modal Multi-Surface Interactive Segmentation
Robin Schön, Julian Lorenz, Katja Ludwig +2
In this paper, we present a method to interactively create segmentation masks on the basis of user clicks. We pay particular attention to the segmentation of multiple surfaces that…
CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations
Julian Lorenz, Mrunmai Phatak, Robin Schön +4
2D scene graphs provide a structural and explainable framework for scene understanding. However, current work still struggles with the lack of accurate scene graph data. To overcom…
Efficient 2D to Full 3D Human Pose Uplifting including Joint Rotations
Katja Ludwig, Yuliia Oksymets, Robin Schön +2
In sports analytics, accurately capturing both the 3D locations and rotations of body joints is essential for understanding an athlete's biomechanics. While Human Mesh Recovery (HM…
On the Importance of Conditioning for Privacy-Preserving Data Augmentation
Julian Lorenz, Katja Ludwig, Valentin Haug +1
Latent diffusion models can be used as a powerful augmentation method to artificially extend datasets for enhanced training. To the human eye, these augmented images look very diff…
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes
Katja Ludwig, Julian Lorenz, Daniel Kienzle +2
The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly dif…
A Fair Ranking and New Model for Panoptic Scene Graph Generation
Julian Lorenz, Alexander Pest, Daniel Kienzle +2
In panoptic scene graph generation (PSGG), models retrieve interactions between objects in an image which are grounded by panoptic segmentation masks. Previous evaluations on panop…
A Review and Efficient Implementation of Scene Graph Generation Metrics
Julian Lorenz, Robin Schön, Katja Ludwig +1
Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years. However, despite these strides, precis…
Adapting the Segment Anything Model During Usage in Novel Situations
Robin Schön, Julian Lorenz, Katja Ludwig +1
The interactive segmentation task consists in the creation of object segmentation masks based on user interactions. The most common way to guide a model towards producing a correct…
Towards Learning Monocular 3D Object Localization From 2D Labels using the Physical Laws of Motion
Daniel Kienzle, Julian Lorenz, Katja Ludwig +1
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead…
The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data
Luuk H. Boulogne, Julian Lorenz, Daniel Kienzle +35
Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Publ…
All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes
Katja Ludwig, Julian Lorenz, Robin Schön +1
Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines. In individual sports, these analyses mainly comprise the body posture.…
Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance
Robin Schön, Katja Ludwig, Rainer Lienhart
Pseudo depth maps are depth map predicitions which are used as ground truth during training. In this paper we leverage pseudo depth maps in order to segment objects of classes that…
Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks
Katja Ludwig, Daniel Kienzle, Julian Lorenz +1
Analyses based on the body posture are crucial for top-class athletes in many sports disciplines. If at all, coaches label only the most important keypoints, since manual annotatio…
Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
Moritz Einfalt, Katja Ludwig, Rainer Lienhart
The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather eff…
COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings
Daniel Kienzle, Julian Lorenz, Robin Schön +2
Since COVID strongly affects the respiratory system, lung CT-scans can be used for the analysis of a patients health. We introduce a neural network for the prediction of the severi…
Recognition of Freely Selected Keypoints on Human Limbs
Katja Ludwig, Daniel Kienzle, Rainer Lienhart
Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points ar…
Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg
Philipp Harzig, Moritz Einfalt, Katja Ludwig +1
The Multimedia and Computer Vision Lab of the University of Augsburg participated in the VTT task only. We use the VATEX and TRECVID-VTT datasets for training our VTT models. We ba…