activity
20242026
collaborators

24 papers

cs.CV2026

Towards Metric-Agnostic Trajectory Forecasting

Markus Knoche, Daan de Geus, Bastian Leibe

Accurate trajectory forecasting of surrounding traffic participants is a core capability for autonomous driving, enabling vehicles to anticipate behavior and plan safe maneuvers. W…

cs.CV2026

SurGe: Improved Surface Geometry in Point Maps

Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt +4

Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface g…

cs.CV2026

Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers

Chung-Shien Brian Wang, Christian Schmidt, Jens Piekenbrinck +1

Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, and MapAnything…

cs.CV2026

Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift

Till Beemelmanns, Alexey Nekrasov, Stefan Vilceanu +4

Reliable uncertainty estimation for 3D object detection is critical for deploying safe autonomous systems, yet modern detectors remain poorly calibrated, especially under distribut…

cs.LG2026

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models

Julia Berger, Bernd Frauenknecht, Sebastian Trimpe +1

Model-based reinforcement learning distinguishes between dynamics models operating on proprioceptive states and latent dynamics models typically operating on high-dimensional image…

cs.CV2026

Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

Kadir Yilmaz, Adrian Kruse, Tristan Höfer +2

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field…