Ziyu Chen

Ph.D. Student in Computer Science
Stanford University

Email: ziyuchen@stanford.edu

I am a first-year PhD student in Computer Science at Stanford University, working in the Stanford Vision and Learning Lab. I am supported by the Stanford Graduate Fellowship.

Previously, I worked with Prof. Yue Wang as a visiting student in GVL at the University of Southern California and collaborated closely with Prof. Marco Pavone from Stanford University. I received my Master’s degree under Prof. Li Song and my Bachelor’s degree from Shanghai Jiao Tong University.

Research Interests

Education

Mar 2025 I am honored to receive the Stanford Graduate Fellowship 🎓 Feb 2025 OmniRe is accepted to ICLR 2025 as Spotlight 🌟 Shout out to all my collaborators! OCT 2024 Talk at MIT Visual Computing Seminar, visited beautiful Boston! 🚣 AUG 2024 Released DriveStudio, a 3DGS system for driving reconstruction/simulation! 🚗 SEP 2023 Joined Geometry, Vision, and Learning Lab as a research intern, advised by Prof. Yue Wang!

The Neverwhere Visual Parkour Benchmark Suite
Ziyu Chen, Haoran Chang, Henghui Bao, Ran Choi, Alan Yu, Ri-Zhao Qiu, Yajvan Ravan, John J. Leonard, Xiaolong Wang, Phillip Isola, Ge Yang †, Yue Wang †
Under Review

A toolchain and benchmark suite for hyper-realistic visual locomotion, building high-fidelity digital twins of real-world environments for closed-loop evaluation.

OmniRe: Omni Urban Scene Reconstruction
Ziyu Chen, Jiawei Yang, Jiahui Huang, Riccardo de Lutio, Janick Martinez Esturo, Boris Ivanovic, Or Litany, Zan Gojcic, Sanja Fidler, Marco Pavone, Li Song, Yue Wang
ICLR 2025 (Spotlight)

OmniRe is a holistic framework for dynamic scene reconstruction that provides comprehensive coverage, including static backgrounds, driving vehicles, and non-rigidly moving dynamic actors.

360-Degree Panorama Generation from Few Unregistered NFoV Images
Jionghao Wang*, Ziyu Chen*, Jun Ling, Rong Xie, Li Song
(* equal contribution)
ACM Multimedia 2023

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.

L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing
Ziyu Chen, Chenjing Ding, Jianfei Guo, Dongliang Wang, Yikang Li, Xuan Xiao, Wei Wu, Li Song
ECCV 2022

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.

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.).