Xinge Yang (杨辛格)

I am a Ph.D. candidate at KAUST Computational Imaging Group, working with Prof. Wolfgang Heidrich. My research focuses on differentiable optical design and end-to-end imaging simulation. I explore the next generation computational cameras for mobile phones and smart glasses, from hardware design and computer vision.

My representative work published in Nature Communications enables automated optical design. Based on this work, I maintain an open-source differentiable optical simulator DeepLens, which enables end-to-end optimization for optics, sensor, and neural network. DeepLens has a growing community with hundreds of users. Feel free to drop me an email if you are also interested!

Email  /  Google Scholar  /  Github  /  LinkedIn  /  知乎

profile photo
Education

  • 2022 - 2026 (expected): Ph.D. in Computer Science, KAUST, Saudi Arabia.
  • 2020 - 2022: M.Sc. in Computer Science, KAUST, Saudi Arabia.
  • 2016 - 2020: B.Sc. in Physics (major) and Computer Science (minor), USTC, China.

    		•
    Working

  • 07/2024 - 11/2024: Research scientist Intern, XR Tech Camera & Sensing, Meta Reality Labs, Sunnyvale, CA, USA.
  • 10/2023 - 01/2024: Research scientist Intern, Optics & Display Research, Meta Reality Labs Research, Redmond, WA, USA

    		•
    Research

    My research focuses on two topics:

  • Differentiable optical design
  • End-to-end imaging simulation

    		•

    First author papers:
    		Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur
    Xinge Yang, Chuong Nguyen, Wenbin Wang, Kaizhang Kang, Wolfgang Heidrich, Ginger Li
    ICCV Workshop 2025. Paper (Arxiv) / Paper (PDF) / Supp (PDF)

  • Efficient and accurate synthetic dataset for real camera defocus deblur without any fine-tuning.

    		•
    		End-to-End Hybrid Refractive-Diffractive Lens Design with Differentiable Ray-Wave Model
    Xinge Yang, Matheus Souza, Kunyi Wang, Praneeth Chakravarthula, Qiang Fu, Wolfgang Heidrich
    Siggraph Asia 2024. Paper (Arxiv) / Paper (PDF) / Supp (PDF)

  • Differentiable ray-wave optical model for end-to-end hybrid refractive-diffractive lens design.

    		•
    		Task-Driven Lens Design for Image Classification
    Xinge Yang, Qiang Fu, Yunfeng Nie, Wolfgang Heidrich
    Arxiv prepint. Paper (Arxiv) / Paper (PDF) / Supp (PDF)

  • Novel lens design objective leveraging a well-trained network to improve computer vision performance with fewer elements.

    		•
    		Aberration-Aware Depth-from-Focus
    Xinge Yang, Qiang Fu, Mohamed Elhoseiny, Wolfgang Heidrich
    TPAMI & ICCP 2023. Paper (IEEE) / Paper (PDF) / Supp (PDF) / Project page / Code

  • Neural PSF representation for accelerated and accurate synthetic data with aberrations and defocus for depth from focus.

    		•
    		Curriculum Learning for ab initio Deep Learned Refractive Optics
    Xinge Yang, Qiang Fu, Wolfgang Heidrich
    Nature Communications 2024. Paper (Nature) / Paper (PDF) / Supp (PDF) / Code / Video

  • First work to demonstrate the superior optimization capability of differentiable optics by automatically designing lenses from scratch.

    		•

    Co-author papers:
    		Tolerance-Aware Deep Optics
    Jun Dai, Liqun Chen, Xinge Yang, Yuyao Hu, Jinwei Gu, Tianfan Xue
    Arxiv prepint 2025. Paper (Arxiv) Project page

  • Considering lens manufacturing tolerances in end-to-end lens design for better optical and computer vision robustness.

    		•
    		End-to-end Optimization of Fluidic Lenses
    Mulun Na, Hector Jimenez-Romero, Xinge Yang, Jonathan Klein, Dominik L. Michels, Wolfgang Heidrich
    Siggraph Asia 2024. Paper (PDF), Project page

  • Differentiable optimization of liquid surface shapes and manufacturing for rapid prototyping.

    		•
    Miscs

  • More about me: I like cats, photography, new techs, and most sports (especially basketball and water sports). I lived in China, Singapore, Saudi Arabia, and the US, and want to live in different places to experience the lifestyle of local people. I enjoy adventures and challenges. I love my life.

  • Peer review statement: I am pleased to be invited for peer review in my research field. I will try my best to complete the review within two weeks. I apply the same high standards to every paper, aiming for the utmost potential of the topic. However, I do not expect the authors to address every suggestion I make and leave the final judgment to the associate editor.

    		•

    Last updated: 10/21/2025 The website template is from Dr. John Barron.