I am a first-year PhD student in Computer Science at Stanford University, working in the Stanford Vision and Learning Lab. Previously, I had the privilege of working closely with Prof. Yue Wang at USC as a visiting student in GVL. I was also fortunate to collaborate with Prof. Marco Pavone at Stanford and Dr. Ge Yang at MIT.
Research Interests
Generative Models
Closed-loop Evaluation & Simulation
Dynamic Scene Modeling
Education
Ph.D. Stanford University
Present
M.S. Shanghai Jiao Tong University
2025
B.E. Shanghai Jiao Tong University
2022
Updates
Mar2025I am honored to receive the Stanford Graduate Fellowship 🎓Feb2025OmniRe is accepted to ICLR 2025 as Spotlight 🌟 Shout out to Prof. Yue and all my collaborators!OCT2024Talk at MIT Visual Computing Seminar, visited beautiful Boston! 🚣AUG2024Released DriveStudio, a 3DGS system for driving reconstruction/simulation! 🚗SEP2023Joined Geometry, Vision, and Learning Lab as a research intern, advised by Prof. Yue Wang!
A toolchain and benchmark suite for hyper-realistic visual locomotion, building high-fidelity digital twins of real-world environments for closed-loop evaluation.
OmniRe is a holistic framework for dynamic scene reconstruction that provides comprehensive coverage, including static backgrounds, driving vehicles, and non-rigidly moving dynamic actors.
We proposed a diffusion-based pipeline that generates complete 360
panoramas using one or more unregistered NFoV images captured from arbitrary
angles.
This pipeline not only delivers superior quality panoramas but also offers a
broader range of outcomes due to its text-conditioned generation capability.
Our L-Tracing based reflectance factorization framework produces photo-realistic novel view images with nearly 10x speedup, compared with the same framework applying volumetric integration for light visibility estimation.
Open-source
A 3DGS codebase for dynamic urban scene reconstruction/simulation, supporting multiple popular driving datasets, including: Waymo, PandaSet, ArgoVerse2, KITTI, NuScenes and NuPlan. It also provides different types of Gaussian representations for reconstructing rigid (Vehicles) and non-rigid individuals (Pedestrians, Cyclists, etc.).