4 papers
GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection
Yutong Yang, Katarina PopoviÄ, Julian Wiederer +3
Detection Transformer (DETR) and its variants show strong performance on object detection, a key task for autonomous systems. However, a critical limitation of these models is that…
LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
Mirlan Karimov, Teodora Spasojevic, Markus Braun +3
Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control…
TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking
Shuxiao Ding, Yutong Yang, Julian Wiederer +4
Query denoising has become a standard training strategy for DETR-based detectors by addressing the slow convergence issue. Besides that, query denoising can be used to increase the…
SVS-GAN: Leveraging GANs for Semantic Video Synthesis
Khaled M. Seyam, Julian Wiederer, Markus Braun +1
In recent years, there has been a growing interest in Semantic Image Synthesis (SIS) through the use of Generative Adversarial Networks (GANs) and diffusion models. This field has…