Zirui Wu

Zirui Wu received his B.Sc. degree in Computer Science and Technology from Beijing Institute of Technology, China.

Since 2022, he has been a research intern at the DISCOVER Lab, Institute for AI Industry Research, Tsinghua University. His research focuses on neural implicit representations, 3D computer vision, robotics, and autonomous driving.

He is currently pursuing his Ph.D. degree in robotics and autonomous systems (ROAS) at the Hong Kong University of Science and Technology (Guangzhou campus), supervised by Prof. Jie Song.

Email  /  CV  /  Google Scholar  /  Github

profile photo

Research

I'm interested in neural implicit represenations, 3D computer vision, robotics, and autonomous driving. Representative papers are highlighted.

MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
Zirui Wu, Tianyu Liu, Liyi Luo, Zhide Zhong, Jianteng Chen, Hongmin Xiao, Chao Hou, Haozhe Lou, Yuantao Chen, Runyi Yang, Yuxin Huang, Xiaoyu Ye, Zike Yan, Yongliang Shi, Yiyi Liao, and Hao Zhao

CICAI, 2023 (Best Paper Runner-up Award)
Project Page / arXiv / GitHub

We propose an autonomous driving simulator based upon neural radiance fields (NeRFs). Compared with existing works, ours has three notable features: (1) Instance-aware. (2) Modular. (3) Realistic. Our simulator achieves state-of-the-art photorealism results given the best module selection. Our simulator will be open-sourced while most of our counterparts are not.

LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF
Zhenxin Zhu, Yuantao Chen, Zirui Wu, Chao Hou, Yongliang Shi, Chuxuan Li, Pengfei Li, Hao Zhao, and Guyue Zhou.

ICRA, 2023
arXiv / GitHub

We propose a two-stage pipeline for global localization in a city-scale neural map.

OmniNeRF: Hybriding Omnidirectional Distance and Radiance fields for Neural Surface Reconstruction
Zirui Wu, Jiaming Shen, Bolin Song, Yi Xu

CMSDA, 2022
arXiv / GitHub

We solve two systematic errors in classical distance-radiance field by utilizing omnidirectional distance field.

Miscellaneaous

I was the team captain of the Kunpeng Baseball Team at Beijing Institute of Technology (BIT) during 2021-2022.

Position: Catcher.
Number: 28 (same with Buster Posey, the former catcher at the San Francisco Giants).
I managed a Coffee shop (supply free coffee on campus, although our activities mainly involved with alcohols :>) during 2020-2022.

Coffee Machine: RANCILIO Class 5 (same as the MacDonald ones).
Representative Drink: A herbal-tea coffee latte, with flavored cream topping.

Invited Talks

[2023/09/02]
MARS: Realistic Neural Real2Sim Simulation for Autonomous Driving (MARS: 基于隐式场的真实感自动驾驶Real2Sim仿真)
@ AutoDrivingTech ("自动驾驶之心" in Chinese).
[2023/08/12]
Towards Realistic Neural Simulator for Autonomous Driving (基于隐式场的真实感自动驾驶仿真器)
@ 3D CVer ("3D 视觉工坊" in Chinese).

Web page borrowed from Jonathan T. Barron. Last update: .