Jun Gao

I am a Ph.D. candidate at the University of Toronto, advised by Prof. Sanja Fidler, and I am affiliated with the Vector Institute. I am also a research scientist at NVIDIA.

My research lies at the intersection of 3D computer vision and computer graphics. I am interested in developing 3D generative AI models to create realistic, high-quality and diverse 3D content for reconstructing, generating and simulating lifelike 3D worlds.

I will join the University of Michigan in the EECS department as an assistant professor in Fall 2025!

Prospective students: I am actively looking for motivated and talented students! If you are interested in joining my group, please read this.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  Pro Bono

profile photo
  • Pro Bono: I decide to commit 1-2 hours per week to host pro bono office hours and provide guidance and mentorship for students, especially people from underrepresented groups. Please check here for more details.
  • May 2024: I will serve as an Area Chair for NeurIPS 2024.
  • Mar. 2024: I will serve on the program committee for SIGGRAPH Asia 2024.
  • Jan. 2024: One paper is accepted to ICLR 2024.
  • Dec. 2023: Our paper received the Best Paper Award at SIGRAPH Aisa 2023.
  • Oct. 2023: I gave a guest lecture at USC and KAIST.
  • Aug. 2023: One paper is accepted to SIGGRAPH Asia 2023.
  • May 2023: I will serve as an Area Chair for NeurIPS 2023.
  • Apr. 2023: I gave talks at PKU, THU, MSRA, and CUHK (Shenzhen) on Machine Learning for 3D Content Creation.
  • Apr. 2023: One paper is accepted to SIGGRAPH 2023.
  • Mar. 2023: Two papers are accepted to CVPR 2023.

  • Publications   (show selected / show by date)

    My research contributes to 3D generative AI by bridging 3D representations from computer graphics with 3D computer vision, and learning to exploit structures from 2D and 3D data. The representations and algorithms I developed are instrumental in the realization of real-world products, including text-to-3D generation at NVIDIA Picasso and 2D image annotation at Toronto Annotation Suite. My research has also been featured at NVIDIA GTC, including image-to-3D generation at GANVerse3D, and 3D asset harvesting at Neural DriveSim.

    Professional Service
    Program Committee: SIGGRAPH Asia 2024.

    Area Chair: NeurIPS 2023, 2024.

    Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH, SIGGRAPH Asia.

    Research scientist at NVIDIA Dec. 2019 - Present

    Research intern at NVIDIA Oct. 2018 - Dec. 2019

    Research intern at Microsoft Research, Asia Sep. 2017 - Jun. 2018

    Mentored Students/Interns
    Tianchang Shen (PhD, CS UofT) Working on differentiable isosurfacing methods.

    Weiwei Sun (PhD, CS UBC) Working on 3D generative models.

    Zian Wang (PhD, CS UofT) Working on lighting decomposition with differentiable renderers.

    Jinchen Xuan (Undergrad, CS PKU) Working on geometric image representation.

    Gary Leung (MSc, CS UofT) Working on Transformer for images.

    Yuxuan Zhang (Undergrad, CS UWaterloo) Working on single image 3D reconstruction.

    Yinan Zhang (Undergrad, CS UWaterloo) Working on single image 3D reconstruction.

    Pro Bono Office Hours
    As a fifth-year PhD student, I always see the information asymmetry between junior students and senior students on problems related to research topics/directions, future career, failure and excitement in research. This problem is more severe for people from underrepresented group.

    Following Krishna, Wei-Chiu and Shangzhe, I decide to commit 1-2 hours per week (mostly on Sunday) to host pro bono office hours and provide guidance, suggestions or mentorship, please fill this form if you are interested.

    I borrowed the template from , ,,.