Search Results for author:
Found 9 papers, 1 papers with code
Transparency Distortion Robustness for SOTA Image Segmentation Tasks
The robustness of semantic segmentation models against distribution shifts caused by differing camera or lighting setups, lens distortions, adversarial inputs and image corruptions has been topic of recent research.
Influence of Water Droplet Contamination for Transparency Segmentation
Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e. g., in the healthcare domain and dangerous environments.
Fast Training Data Acquisition for Object Detection and Segmentation using Black Screen Luminance Keying
Instead of chroma keying, we propose luminance keying for fast and straightforward training image acquisition.
One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model
Estimating the 3D shape of an object using a single image is a difficult problem.
Extending 6D Object Pose Estimators for Stereo Vision
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task.
A Concept for Reconstructing Stucco Statues from historic Sketches using synthetic Data only
In medieval times, stuccoworkers used a red color, called sinopia, to first create a sketch of the to-be-made statue on the wall.
Detection and Pose Estimation of flat, Texture-less Industry Objects on HoloLens using synthetic Training
Current state-of-the-art 6d pose estimation is too compute intensive to be deployed on edge devices, such as Microsoft HoloLens (2) or Apple iPad, both used for an increasing number of augmented reality applications.
YCB-Ev: Event-vision dataset for 6DoF object pose estimation
Our work introduces the YCB-Ev dataset, which contains synchronized RGB-D frames and event data that enables evaluating 6DoF object pose estimation algorithms using these modalities.
Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
Given the dependency of current CNN architectures on a large training set, the possibility of using synthetic data is alluring as it allows generating a virtually infinite amount of labeled training data.
