Georg Hess

Gothenburg, Sweden

Previously, I did an industrial PhD at Zenseact and Chalmers, supervised by Lennart Svensson and Christoffer Petersson, working on neural sensor simulation (NeuRAD, SplatAD), self-supervised learning for lidar (Voxel-MAE, LidarCLIP), and probabilistic perception. Co-author of the Zenseact Open Dataset.

news

Jul 31, 2025	I’ve started building something new
May 25, 2025	I successfully defended my PhD thesis, Pensieve Perception: Uncertainty, Language, and Novel Views for Autonomous Driving, at Chalmers
Feb 27, 2025	SplatAD was accepted to CVPR 2025, and will be presented orally at the DDADS workshop!

selected publications

SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving

Georg Hess, Carl Lindström, Maryam Fatemi, and 2 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

arXiv Bib Code Website

@inproceedings{hess2024splatad,
  title = {SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving},
  author = {Hess, Georg and Lindstr{\"o}m, Carl and Fatemi, Maryam and Petersson, Christoffer and Svensson, Lennart},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  month = jun,
  pages = {11982-11992},
}

NeuRAD: Neural Rendering for Autonomous Driving

Adam Tonderski, Carl Lindström, Georg Hess, and 3 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024

Highlight arXiv Bib Code Website

Selected as a highlight at CVPR 2024 (top 11% of accepted papers)

@inproceedings{tonderski2024neurad,
  title = {NeuRAD: Neural Rendering for Autonomous Driving},
  author = {Tonderski, Adam and Lindstr{\"o}m, Carl and Hess, Georg and Ljungbergh, William and Svensson, Lennart and Petersson, Christoffer},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2024},
  pages = {14895-14904},
}

LidarCLIP or: How I Learned to Talk to Point Clouds

Georg Hess^*, Adam Tonderski^*, Christoffer Petersson, and 2 more authors

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2024

arXiv Bib Code Website

@inproceedings{hess2024lidarclip,
  title = {LidarCLIP or: How I Learned to Talk to Point Clouds},
  author = {Hess, Georg and Tonderski, Adam and Petersson, Christoffer and {\AA}str{\"o}m, Kalle and Svensson, Lennart},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2024},
  month = jan,
}

Object Detection as Probabilistic Set Prediction

Georg Hess, Christoffer Petersson, and Lennart Svensson

In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part X, Oct 2022

DOI arXiv Bib Code Website

@inproceedings{hess2022object,
  title = {Object Detection as Probabilistic Set Prediction},
  author = {Hess, Georg and Petersson, Christoffer and Svensson, Lennart},
  booktitle = {Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part X},
  pages = {550--566},
  year = {2022},
  month = oct,
  organization = {Springer},
  doi = {https://doi.org/10.1007/978-3-031-20080-9_32},
}

Masked Autoencoder for Self-Supervised Pre-Training on Lidar Point Clouds

Georg Hess, Johan Jaxing, Elias Svensson, and 3 more authors

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, Jan 2023

DOI arXiv Bib Code Website

@inproceedings{hess2023masked,
  title = {Masked Autoencoder for Self-Supervised Pre-Training on Lidar Point Clouds},
  author = {Hess, Georg and Jaxing, Johan and Svensson, Elias and Hagerman, David and Petersson, Christoffer and Svensson, Lennart},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops},
  pages = {350--359},
  year = {2023},
  month = jan,
  doi = {10.1109/WACVW58289.2023.00039},
}