OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

(Category-level 6D pose estimation in traffic scenes. 3D object detector)
OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
Yongzhi Su, Yan Di, Fabian Manhardt, Guangyao Zhai, Jason Rambach, Benjamin Busam, Didier Stricker, and Federico Tombari.
IEEE Robotics and Automation Letters (RAL), (in print), 2023.
[pdf] [bibtex]

@inproceedings{ OPA3D,
    author    = { Yongzhi Su and Yan Di and Fabian Manhardt and Guangyao Zhai and Jason Rambach and Benjamin Busam and Didier Stricker and Federico Tombari },
  title={OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection},
  author={Yongzhi Su*, Yan Di*, Fabian Manhardt, Guangyao Zhai, Jason Rambach, Benjamin Busam, Didier Stricker, Federico Tombari},
  journal={arXiv preprint arXiv:2211.01142},
  year={2023}
}
  }