3 papers
cs.CV2026
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…
cs.CV2026
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…
cs.CV2025
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…