Ziyu Chen

Ph.D. Student in Computer Science
Stanford University

About Me

I am a first-year CS Ph.D. student at Stanford University, advised by Jiajun Wu. My research is generously supported by the Stanford Graduate Fellowship. I'm working on visual generative models.

Previously, I worked with Prof. Yue Wang at USC and collaborated closely with Prof. Marco Pavone. I received my M.S. and B.S. degrees from Shanghai Jiao Tong University.

Updates

Mar 2025 Awarded 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.

Research

◆ equal contribution · ◇ equal advising · full list

	RealWonder: Real-Time Physical Action-Conditioned Video Generation ◆Wei Liu, ◆Ziyu Chen, Zizhang Li, Yue Wang, ◇Hong-Xing Yu, ◇Jiajun Wu Under Review Abstract ● Paper RealWonder turns a single image into an interactive scene using a controllable video model. By incorporating physics, it enables physically grounded 3D interactions.
	The Neverwhere Visual Parkour Benchmark Suite Ziyu Chen, Henghui Bao, Haoran Chang, Alan Yu, Ran Choi, Kai McClennen, Gio Huh, Kevin Yang, Ri-Zhao Qiu, Yajvan Ravan, John J. Leonard, Xiaolong Wang, Phillip Isola, ◇Ge Yang, ◇Yue Wang Under Review Abstract ● Paper ● Website 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) Abstract ● Paper ● Website ● Code ● Review 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 ACM Multimedia 2023 Abstract ● Paper ● Code 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 Abstract ● Paper ● Code 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 and simulation, featuring different Gaussian representations for rigid actors (vehicles) and non-rigid actors (pedestrians, cyclists, etc.). Supported datasets include Waymo, PandaSet, ArgoVerse2, KITTI, NuScenes, NuPlan.

Recent Talks

OmniRe: Omni Urban Scene Reconstruction

MIT, Visual Computing Seminar, Oct 2024
Peking University, Hyperplane Lab, Oct 2024
LiAuto, Sept 2024

Honors & Awards

Stanford Graduate Fellowship, Stanford, 2025

National Scholarship, Shanghai Jiao Tong University, 2023

Zhiyuan Honor Fellowship, Shanghai Jiao Tong University, 2018-2022