|
Xinge Yang (杨辛格)
I am a Ph.D. student at KAUST Computational Imaging Group, working with Prof. Wolfgang Heidrich. My research interests include deep learning for optical design, computational cameras, and optics-aware computational photography.
I maintain an awesome differentiable ray tracer DeepLens. It can do differentiable simulation of camera lens captures and optimize the optics. Feel free to drop me an email if you are interested!
Email /
Google Scholar /
Github /
LinkedIn /
知乎
|
|
|
News
08/2024: "Curriculum Learning for ab initio Deep Learned Refractive Optics" is acceptted by Nature Communications!
03/2024: DeepLens is open-sourced, build your End-to-End lens design pipeline with 5 lines of Python code!
10/2023: I started my internship at Meta, working on gradient-based optical design for AR waveguide.
09/2023: We released an automated lens design demo AutoLens .
07/2023: Our paper, "Aberration-Aware Depth-from-Focus" is accepted by ICCP and TPAMI.
|
|
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 - now: Research Scientist Intern, Meta Camera & Depth Team, Sunnyvale, CA.
10/2023 - 01/2024: Research Scientist Intern, Meta Optics & Display Research, Redmond, WA.
|
|
Research
I do differentiable optical simulation, and apply it to different applications.
Deep learning for optical design
Computational cameras
Optics-aware computational photography
|
|
|
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 / paper (pdf) / supp (pdf)
Differentiable ray-tracing and wave-propagation model.
End-to-End hybrid refractive-diffractive lenses design with prototypes.
|
|
|
Image Quality Is Not All You Want: Task-Driven Lens Design for Image
Classification
Xinge Yang, Qiang Fu, Yunfeng Nie, Wolfgang Heidrich
Arxiv prepint. paper / paper (pdf) / supp (pdf)
A new End-to-End optical design methedology: a well-trained network as objective.
TaskLens: better computer vision performance with fewer lens elements.
|
|
|
Aberration-Aware Depth-from-Focus
Xinge Yang, Qiang Fu, Mohamed Elhoseiny, Wolfgang Heidrich
TPAMI & ICCP 2023. paper / paper (pdf) / supp (pdf) / project / code
An implicite network for real-lens spatially-varying focus-dependent (4D) PSFs representation.
Generalize depth-from-focus network from synthetic data to real data by considering optical aberrations.
|
|
|
Curriculum Learning for ab initio Deep Learned Refractive Optics
Xinge Yang, Qiang Fu, Wolfgang Heidrich
Nature Communications 2024. paper / paper (pdf) / supp (pdf) / code / video
Automated lens design from scratch with differentiable ray tracing.
DeepLens framework for (1) differentiable ray tracing simulation, (2) end-to-end lens-network co-design.
|
|
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.
|
|
