CITATION.md

October 2, 2025 ยท View on GitHub

Cite DeepLens papers

Differentiable optics was developed by the KAUST Computational Imaging Group (https://vccimaging.org/). The first version of differentiable ray tracer was implemented by Dr. Congli Wang on Mitsuba2 in the following paper:

@article{sun2021end,
  title={End-to-end complex lens design with differentiable ray tracing},
  author={Sun, Qilin and Wang, Congli and Qiang, Fu and Xiong, Dun and Wolfgang, Heidrich},
  journal={ACM Trans. Graph},
  volume={40},
  number={4},
  pages={1--13},
  year={2021}
}

Later, Dr. Congli Wang implemented the first PyTorch version of differentiable ray tracer (dO) in the following paper:

@article{wang2022differentiable,
  title={do: A differentiable engine for deep lens design of computational imaging systems},
  author={Wang, Congli and Chen, Ni and Heidrich, Wolfgang},
  journal={IEEE Transactions on Computational Imaging},
  volume={8},
  pages={905--916},
  year={2022},
  publisher={IEEE}
}

Currently, Xinge Yang is building and maintaining DeepLens. The automated lens design work demonstrates the outstanding capability of differentiable optics compared to classical optical design in the following paper:

@article{yang2024curriculum,
  title={Curriculum learning for ab initio deep learned refractive optics},
  author={Yang, Xinge and Fu, Qiang and Heidrich, Wolfgang},
  journal={Nature communications},
  volume={15},
  number={1},
  pages={6572},
  year={2024},
  publisher={Nature Publishing Group UK London}
}

A novel differentiable ray-wave model is introduced for simulating and optimizing hybrid refractive-diffractive lenses in the following paper:

@inproceedings{yang2024end,
  title={End-to-end hybrid refractive-diffractive lens design with differentiable ray-wave model},
  author={Yang, Xinge and Souza, Matheus and Wang, Kunyi and Chakravarthula, Praneeth and Fu, Qiang and Heidrich, Wolfgang},
  booktitle={SIGGRAPH Asia 2024 Conference Papers},
  pages={1--11},
  year={2024}
}