Search Results for author: Thomas H. Kolbe

Found 3 papers, 2 papers with code

RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning

no code implementations16 Apr 2025 Yuan Luo, Rudolf Hoffmann, Yan Xia, Olaf Wysocki, Benedikt Schwab, Thomas H. Kolbe, Daniel Cremers

Moreover, we propose a novel neural network, RADLER, leveraging the effectiveness of contrastive self-supervised learning (SSL) and semantic 3D city models to enhance radar object detection of pedestrians, cyclists, and cars.

Object object-detection +3

FacaDiffy: Inpainting Unseen Facade Parts Using Diffusion Models

1 code implementation20 Feb 2025 Thomas Froech, Olaf Wysocki, Yan Xia, Junyu Xie, Benedikt Schwab, Daniel Cremers, Thomas H. Kolbe

To address this challenge, we introduce FacaDiffy, a novel method for inpainting unseen facade parts by completing conflict maps with a personalized Stable Diffusion model.

Cannot find the paper you are looking for? You can Submit a new open access paper.