You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This evaluation script computes the Average Precision (AP) for 3D bounding box predictions at an IoU threshold of 0.5. In contrast to KITTI, Waymo and NuScenes evaluation code, it accounts for full SO(3) rotation. Please find our project page here:
CARLA Drone: Monocular 3D Object Detection from a Different Perspective
The code is primarily based on PyTorch3D and Cube R-CNN and serves as a stand-alone evaluation script.
Therefore, this code is also licenced under CC-BY-NC 4.0.
Citations
@article{meier2024cdrone,
author = {Meier, Johannes and Scalerandi, Luca and Dhaouadi, Oussema and Kaiser, Jacques and Araslanov Nikita and Cremers, Daniel},
title = {{CARLA Drone:} Monocular 3D Object Detection from a Different Perspective},
journal = {GCPR},
year = {2024},
}
@inproceedings{brazil2023omni3d,
author = {Garrick Brazil and Abhinav Kumar and Julian Straub and Nikhila Ravi and Justin Johnson and Georgia Gkioxari},
title = {{Omni3D}: A Large Benchmark and Model for {3D} Object Detection in the Wild},
booktitle = {CVPR},
address = {Vancouver, Canada},
month = {June},
year = {2023},
organization = {IEEE},
}