Our perception teams from Mercedes-Benz AG were at the International Conference on Computer Vision (ICCV) in Paris last week 📷

I went there together with my colleagues Fabian Poggenhans, Peizheng Li, Shuxiao Ding, Vitali Kaiser, You Zhou, Andrea Ramazzina, and Stefanie Walz.

In addition to networking and discussing about cool new research, some of us also presented our latest research in the area of automated driving in form of three papers:

👉 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
Authors: Shuxiao Ding, Eike Rehder, Lukas Schneider, Marius Cordts, Juergen Gall
Read here

👉 ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering
Authors: Andrea Ramazzina, Mario Bijelic, Stefanie Walz, Alessandro Sanvito, Dominik Scheuble, Felix Heide
Read here

👉 PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird’s-Eye View
Authors: Peizheng Li, Shuxiao Ding, Xieyuanli Chen, Niklas Hanselmann, Marius Cordts, Juergen Gall
Read here
(originally published at IJCAI 2023; presented at the ROAD++ Workshop)