publications

2024

2024

  1. emperror_dynamic_teaser.webp
    EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving Planners
    Niklas Hanselmann, Simon Doll, Marius Cordts, Hendrik P.A. Lensch, and Andreas Geiger
    arXiv, 2024
    PDF Video Website
  2. dualad_teaser.webp
    DualAD: Disentangling the Dynamic and Static World for End-to-End Driving
    Simon Doll, Niklas Hanselmann , Lukas Schneider, Richard Schulz, Marius Cordts, Markus Enzweiler, and Hendrik P.A. Lensch
    Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    PDF Video Website
  3. startrack_thumbnail.jpg
    Oral   STAR-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations
    Simon Doll, Niklas Hanselmann , Lukas Schneider, Richard Schulz, Markus Enzweiler, and Hendrik P.A. Lensch
    Robotics and Automation Letters (RA-L), 2024
    Presented at International Conference on Intelligent Robots and Systems (IROS), 2024
    PDF Video Website

2023

2023

  1. powerbev_thumbnail.gif
    PowerBEV: A Powerful yet Lightweight Framework for Instance Prediction in Bird’s-Eye View
    Peizheng Li, Shuxiao Ding, Xieyuanli Chen, Niklas Hanselmann, Marius Cordts, and Jürgen Gall
    International Joint Conference on Artificial Intelligence (IJCAI), 2023
    PDF Code

2022

2022

  1. king_animated_thumbnail.gif
    Oral   KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
    Niklas Hanselmann, Katrin Renz, Kashyap Chitta, Apratim Bhattacharyya, and Andreas Geiger
    European Conference on Computer Vision (ECCV), 2022
    PDF Supp Video Code Poster Website
  2. labelshift_thumbnail.jpg
    Unsupervised Domain Adaptive Object Detection with Class Label Shift Weighted Local Features
    Andong Tan, Niklas Hanselmann, Shuxiao Ding, Federico Tombari, and Marius Cordts
    ECCV Workshop on Learning from Limited and Imperfect Data (L2ID), 2022
    PDF

2021

2021

  1. wsda_thumbnail.jpg
    Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation
    Niklas Hanselmann, Nick Schneider, Benedikt Ortelt, and Andreas Geiger
    IEEE Intelligent Vehicles Symposium (IV), 2021
    PDF Supp Video

2019

2019

  1. vgnms_thumbnail.png
    Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
    Nils Gählert, Niklas Hanselmann, Uwe Franke, and Joachim Denzler
    NeuRIPS Workshop on Machine Learning for Autonomous Driving, 2019
    PDF