Jianfei Guo

Jianfei Guo (郭建非)

[Current position to be updated soon]

My current focus is on building next-gen simulation systems for autonomous vehicles, robots, and more, while also pushing the boundaries of research in neural rendering, neural reconstruction, and neural graphics.

Previously, I was a research engineer at Shanghai AI Lab’s ADLab, where I initiated the 3DNR team, built the open-source project neuralsim from scratch, and conducted research related to multi-view implicit surface reconstruction and efficient large-scale/generative neural scene representations. Prior to that, I was a research intern at Huawei for two years, where I gradually shifted my interests from embedded systems to machine learning. I received my banchelor’s degree at Xi’an Jiaotong University from the elite class named after Tsien Hsue-Shen ^{(钱学森班)}.

My life goal is to make AI that trully understands ours 3D world and its rich scientific laws, and let AI aid us human race to think, to innovate, to research and to create, and boost mankind’s voyage to the wide sea of stars someday.

Contact: ffventus [at] gmail.com

news

Jul 6, 2021	Joining Shanghai AI Lab as a researcher!
Jul 2, 2021	Graduated from Xi’an Jiaotong University.
Sep 4, 2018	Joining 2012 Lab., Huawei Technologies Co., Ltd. as an intern!

selected publications

arXiv

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

Bo Zhang, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, and others

arXiv preprint arXiv:2309.05527, 2023

Abs arXiv Bib

@article{zhang2023resimad,
  title = {ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation},
  author = {Zhang, Bo and Cai, Xinyu and Yuan, Jiakang and Yang, Donglin and Guo, Jianfei and Xia, Renqiu and Shi, Botian and Dou, Min and Chen, Tao and Liu, Si and others},
  journal = {arXiv preprint arXiv:2309.05527},
  year = {2023}
}

arXiv

StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views

Jianfei Guo, Nianchen Deng, Xinyang Li, Yeqi Bai, Botian Shi, Chiyu Wang, Chenjing Ding, Dongliang Wang, and Yikang Li

arXiv preprint arXiv:2306.04988, 2023

arXiv Bib Code Website

@article{guo2023streetsurf,
  title = {StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views},
  author = {Guo, Jianfei and Deng, Nianchen and Li, Xinyang and Bai, Yeqi and Shi, Botian and Wang, Chiyu and Ding, Chenjing and Wang, Dongliang and Li, Yikang},
  journal = {arXiv preprint arXiv:2306.04988},
  year = {2023}
}

ECCV

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, and Li Song

In Proc. European Conference on Computer Vision (ECCV), 2022

Bib

@inproceedings{chen2022tracing,
  title = {L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing},
  author = {Chen, Ziyu and Ding, Chenjing and Guo, Jianfei and Wang, Dongliang and Li, Yikang and Xiao, Xuan and Wu, Wei and Song, Li},
  booktitle = {Proc. European Conference on Computer Vision (ECCV)},
  pages = {217--233},
  year = {2022}
}

arXiv

Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images

Jianfei Guo, Zhiyuan Yang, Xi Lin, and Qingfu Zhang

arXiv preprint arXiv:2111.04237, 2021

arXiv Bib

@article{guo2021template,
  title = {Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images},
  author = {Guo, Jianfei and Yang, Zhiyuan and Lin, Xi and Zhang, Qingfu},
  journal = {arXiv preprint arXiv:2111.04237},
  year = {2021}
}