publications

2023

  1. 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
    arXiv 2023
    PDF Website Video
  2. 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

  1. 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 Code Website Video Poster
  2. 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

  1. 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

  1. 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