4 papers
CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation
Leon Sick, Dominik Engel, Sebastian Hartwig +2
Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have eme…
HPSCAN: Human Perception-Based Scattered Data Clustering
Sebastian Hartwig, Christian van Onzenoodt, Dominik Engel +2
Cluster separation is a task typically tackled by widely used clustering techniques, such as k-means or DBSCAN. However, these algorithms are based on non-perceptual metrics, and o…
A Survey on Quality Metrics for Text-to-Image Generation
Sebastian Hartwig, Dominik Engel, Leon Sick +6
AI-based text-to-image models do not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content. Consequently, th…
AutoTherm: A Dataset and Benchmark for Thermal Comfort Estimation Indoors and in Vehicles
Mark Colley, Sebastian Hartwig, Albin Zeqiri +2
Thermal comfort inside buildings is a well-studied field where human judgment for thermal comfort is collected and may be used for automatic thermal comfort estimation. However, in…