Arpit Jadon

I am currently a research engineer at the German Aerospace Center in Berlin, mostly working on computer vision applications in autonomous driving and transporation systems.

Prior to that, I worked as a research engineer at Max Planck Institute for Informatics in Saarbrücken. I did my Master's in Computer Science from Saarland University with a focus on computer vision and machine learning. During my Master thesis, I worked in the computer vision and machine learning department at the Max Planck Institute for Informatics with Dr. Dengxin Dai and Dr. Lukas Hoyer on synthetic to real domain adaptive semantic segmentation for autonomous driving.

Email  /  CV  /  Scholar  /  Linkedin

profile photo

Research

I'm interested in solving critical problems like medical imaging and autonomous driving using computer vision and machine learning. More specific areas of interests include multimodal and label efficient learning, domain adaptation, synthetic data generation, and scene understanding.

RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving
Arpit Jadon, Haoran Wang, Phillip Thomas, Michael Stanley, S. Nathaniel Cibik, Rachel Laurat, Omar Maher, Lukas Hoyer, Ozan Unal, Dengxin Dai

IEEE Intelligent Vehicles Symposium (IV) 2025
Paper / Dataset

A multi-modal multi-task synthetic dataset for autonomous driving with high realism and diversity.

ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
Christos Sakaridis*, Haoran Wang*, Ke Li, Rene Zurbruegg, Arpit Jadon, Wim Abbeloos, Daniel Olmeda Reino, Luc Van Gool, Dengxin Dai

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2025
Paper / Dataset

An Adverse Conditions Dataset with Correspondences (ACDC) for training and testing methods for diverse semantic perception tasks on adverse visual conditions.


Design and source code borrowed from Jon Barron's website.