Shijie Zhou

Shijie Zhou

Ph.D. Student at UCLA

I am a Ph.D. student in Electrical and Computer Engineering at University of California, Los Angeles advised by Prof. Achuta Kadambi. Previously, I obtained my M.S. in Electrical Engineering from Columbia University in 2021, where I was fortunate to be advised by Prof. John Wright. I received my B.E. in Electronic Information Engineering from University of Electronic Science and Technology of China (UESTC) in 2019.

My research interest includes computer vision, computational imaging and generative AI. Currently, I am focusing on 3D vision using both neural (implicit) and physical (explicit) representations. I am also actively collaborating with the groups of Prof. Leonidas Guibas at Stanford University and Prof. Atlas Wang at University of Texas at Austin.

I will be joining Google as a Student Researcher in Summer 2024.

🔥 News

  • 2024.04: Feature 3DGS was selected as a Highlight paper at CVPR 2024 (2.8% of 11532 submissions)! 🎉
  • 2024.02: One paper accepted to CVPR 2024.
  • 2023.02: One paper accepted to CVPR 2023.
  • 2021.09: Awarded Graduate Dean’s Scholar Award from UCLA.
  • 2020.06: Awarded MS Honors Student from Columbia University.

📝 Selected Publications

* indicates equal contribution

arXiv
sym

DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

Shijie Zhou*, Zhiwen Fan*, Dejia Xu*, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, Achuta Kadambi

Paper | Project

  • We introduce a 3D scene generation pipeline that creates immersive scenes with full 360$^{\circ}$ coverage from text prompts of any level of specificity.
CVPR 2024
sym

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

Shijie Zhou, Haoran Chang*, Sicheng Jiang*, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi

Paper | Project (CVPR 2024 Highlight)

  • Feature 3DGS 🪄, distills feature fields from 2D foundation models, opening the door to a brand new semantic, editable, and promptable explicit 3D scene representation.
CVPR 2023
sym

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

Zhen Wang*, Shijie Zhou*, Jeong Joon Park, Despoina Paschalidou, Suya You, Gordon Wetzstein, Leonidas Guibas, Achuta Kadambi

Paper | Project

  • Rethinking latent topologies for fast and detailed implicit 3D reconstructions.

🎖 Honors and Awards

  • 2021 Graduate Dean’s Scholar Award, UCLA
  • 2020 MS Honors Student, Columbia University
  • 2019 Outstanding Graduate, University of Electronic Science and Technology of China
  • 2017-2018 James Watt Scholar, University of Glasgow

💻 Experience

  • 2024.06 - 2024.09, Student Researcher at Google
  • 2023.06 - 2023.09, Visiting Academic at USC Institute for Creative Technologies

📖 Teaching

  • Teaching Assistant @ UCLA: ECE188 Computer Vision, ECE113 Digital Signal Processing
  • Teaching Assistant @ Columbia: EECS6690 Statistical Learning, ELEN6885 Reinforcement Learning
  • Teaching Assistant @ UoG & UESTC: 1008 Microelectronic Systems, 3010 Team Design Project and Skills

🖋️ Services

  • Reviewer: ECCV 2024, AI for 3D Content Creation @ ICCV 2023