CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

Rui Song, Chenwei Liang, Yan Xia, Walter Zimmer, Hu Cao, Holger Caesar, Andreas Festag, Alois Knoll (paper)

arXiv 2025

LeAP: Consistent multi-domain 3D labeling using Foundation Models

Simon Gebraad, Andras Palffy, Holger Caesar (paper)

ICRA 2025

TU Delft Mobility Futures: Four scenarios for the Dutch mobility system in 2050

Manuela Triggianese, Deborah Nas, Stefan van der Spek, Serge Hoogendoorn, Achilleas Psyllidis, Nicole van Nes, Holger Caesar, Wijnand Veeneman, Yousef Maknoon, Bilge Atasoy (paper)

TU Delft

Advancing High-Resolution and Efficient Automotive Radar Imaging through Domain-Informed 1D Deep Learning

Ruxin Zheng, Shunqiao Sun, Hongshan Liu, Holger Caesar, Honglei Chen, Jian Li (paper)

ICASSP 2025

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

Zijian Zhou, Zheng Zhu, Holger Caesar, Miaojing Shi (paper)

ECCV 2024

OSSA: Unsupervised One-Shot Style Adaptation

Robin Gerster, Holger Caesar, Matthias Rapp, Alexander Wolpert, Michael Teutsch (paper)

ECCV 2024 workshop

Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving

Karim Armanious, Maurice Quach, Michael Ulrich, (...), Holger Caesar (paper)

arXiv 2024

UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes

Ted Lentsch, Holger Caesar, Dariu M. Gavrila (paper)

NeurIPS 2024

Methods and systems for traffic light labelling via motion inference

Holger Caesar, Whye Kit Fong, Abirami Srinivasan, Dimitrios Panagiotis Geromichalos (patent)

US Patent US20240123996A1, published 18/04/2024

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

William Ljungbergh, Adam Tonderski, Joakim Johnander, Holger Caesar, Kalle Åström, Michael Felsberg, Christoffer Petersson (paper)

ECCV 2024

Multi-FEAT: Multi-Feature Edge AlignmenT for Targetless Camera-LiDAR Calibration

Bichi Zhang, Holger Caesar, Raj Thilak Rajan (paper)

ICRA 2024 workshop

Label-Efficient 3D Object Detection For Road-Side Units

Minh-Quan Dao, Holger Caesar, Julie Stephany Berrio et al. (paper)

IV 2024

DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection

Felix Fent, Andras Palffy, Holger Caesar (paper)

T-IV 2024

ICP-Flow: LiDAR Scene Flow Estimation with ICP

Yancong Lin, Holger Caesar (paper)

CVPR 2024, Winner of the Argoverse Scene Flow Challenge 2024 in the unsupervised track

Offline Tracking with Object Permanence

Xianzhong Liu, Holger Caesar (paper)

IV 2024 Oral (top 5% of all accepted papers), Best Paper Award Finalist

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

Shiming Wang, Holger Caesar, Liangliang Nan, Julian F. P. Kooij (paper)

IV 2024

Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving

Napat Karnchanachari, Dimitris Geromichalos, Kok Seang Tan, (...), Holger Caesar (paper)

ICRA 2024

BaSAL: Size Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

Jiarong Wei, Yancong Lin, Holger Caesar (paper)

ICRA 2024

VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation

Zijian Zhou, Miaojing Shi, Holger Caesar (paper)

arXiv 2023

Graph Convolutional Networks for Complex Traffic Scenario Classification

Tobias Hoek, Holger Caesar, Andreas Falkoven, Tommy Johansson (paper)

NCCV 2023

Lanelet2 for nuScenes: Enabling Spatial Semantic Relationships and Diverse Map-Based Anchor Paths

Alexander Naumann, Felix Hertlein, (...), Holger Caesar (paper)

CVPR workshop 2023

Automated verification of annotated sensor data

Kok-Seang Tan, Holger Caesar, Yiluan Guo, Oscar Beijbom (patent)

US patent 17/450,362

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

Zijian Zhou, Miaojing Shi, Holger Caesar (paper, homepage)

ICCV 2023

Cross-modality Active Learning for Object Detection

Kok Seang Tan, Holger Caesar, Oscar Beijbom (patent)

US patent 17363085, published 01/05/2023

Automatically choosing data samples for annotation

Holger Caesar, Oscar Beijbom (patent)

US patent 11521010, published 12/06/2022

Adding tags to sensor data via a plurality of models and querying the sensor data

Qiang Xu, Oscar Beijbom, Holger Caesar et al. (patent)

US patent 11488377, published 11/01/2022

SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

Ted Lentsch, Zimin Xia, Holger Caesar, Julian Kooij (paper, homepage, poster)

CVPR 2023

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

Whye-Kit Fong, (...), Holger Caesar, (...) Abhinav Valada (paper, homepage)

ICRA 2022

nuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

Holger Caesar, Juraj Kabzan, Kok Seang Tan et al. (paper, homepage)

CVPR workshop 2021

The Efficacy of Neural Planning Metrics: A Meta-Analysis of PKL on nuScenes

Yiluan Guo, Holger Caesar, Oscar Beijbom et al. (paper)

IROS workshop 2021

nuScenes: A Multimodal Dataset for Autonomous Driving

Holger Caesar, Varun Bankiti, Alex H. Lang et al. (paper, homepage)

CVPR 2020

PointPillars: Fast Encoders for Object Detection from Point Clouds

Alex H Lang, Sourabh Vora, Holger Caesar et al. (paper, homepage)

CVPR 2019

COCO-Stuff: Thing and Stuff Classes in Context

Holger Caesar, Jasper Uijlings, Vittorio Ferrari (paper, homepage)

CVPR 2018

Weakly Supervised Object Localization Using Things and Stuff Transfer

Miaojing Shi, Holger Caesar, Vittorio Ferrari (paper)

ICCV 2017

Region-Based Semantic Segmentation with End-to-End Training

Holger Caesar, Jasper Uijlings, Vittorio Ferrari (paper, homepage)

ECCV 2016

Joint Calibration for Semantic Segmentation

Holger Caesar, Jasper Uijlings, Vittorio Ferrari (paper)

BMVC 2015