Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering

Stefan Hein Bengtson, Hampus Åsträm, Thomas B. Moeslund, Elin Anna Topp, Volker Krüger. Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering. In IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021, Prague, Czech Republic, September 27 - Oct. 1, 2021. pages 4618-4624, IEEE, 2021. [doi]

@inproceedings{BengtsonAMTK21,
  title = {Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering},
  author = {Stefan Hein Bengtson and Hampus Åsträm and Thomas B. Moeslund and Elin Anna Topp and Volker Krüger},
  year = {2021},
  doi = {10.1109/IROS51168.2021.9636839},
  url = {https://doi.org/10.1109/IROS51168.2021.9636839},
  researchr = {https://researchr.org/publication/BengtsonAMTK21},
  cites = {0},
  citedby = {0},
  pages = {4618-4624},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021, Prague, Czech Republic, September 27 - Oct. 1, 2021},
  publisher = {IEEE},
  isbn = {978-1-6654-1714-3},
}