This repository contains the upgraded code for the CVPR 2022 paper EPro-PnP, featuring improved models for both the 6DoF and 3D detection benchmarks.

A new updated preprint can be found on arXiv: EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation.

Main differences to v1b:

• Use GaussianMixtureNLLLoss as auxiliary coordinate regression loss
• Add auxiliary depth and bbox losses

At the time of submission (Aug 30, 2022), EPro-PnP-Det v2 ranks 1st among all camera-based single-frame object detection models on the official nuScenes benchmark (test split, without extra data).

Main differences to v1b:

• Improve w2d scale handling (very important)
• Improve network initialization
• Adjust loss weights

With these updates the v2 model can be trained without 3D models to achieve better performance (ADD 0.1d = 93.83) than GDRNet (ADD 0.1d = 93.6), unleashing the full potential of simple end-to-end training.

If you find this project useful in your research, please consider citing:

@inproceedings{epropnp, 
  author = {Hansheng Chen and Pichao Wang and Fan Wang and Wei Tian and Lu Xiong and Hao Li, 
  title = {EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation}, 
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, 
  year = {2022}
}