Search Results for author:
Found 6 papers, 2 papers with code
Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency
We propose a novel loss function, multiview consistency, to enable adding additional training data with only 2D supervision.
BugNIST - a Large Volumetric Dataset for Object Detection under Domain Shift
Annotated training data is essential for deep learning-based object detection.
SportsPose -- A Dynamic 3D sports pose dataset
Accurate 3D human pose estimation is essential for sports analytics, coaching, and injury prevention.
Sparse-View Spectral CT Reconstruction Using Deep Learning
Furthermore, the results indicate that the network can exploit the coupling of the channels to enhance the overall quality and robustness.
Multi-Spectral Imaging via Computed Tomography (MUSIC) - Comparing Unsupervised Spectral Segmentations for Material Differentiation
Multi-spectral computed tomography is an emerging technology for the non-destructive identification of object materials and the study of their physical properties.
Content-based Propagation of User Markings for Interactive Segmentation of Patterned Images
Since we combine a limited amount of user-labelled data with the clustering information obtained from the unlabelled parts of the image, our method fits in the general framework of semi-supervised learning.
