I’m currently a research scientist & PI at Shanghai AI Laboratory.
I am leading a research team containg over 20 talented researchers at Shanghai AI Lab, aiming at innovating to the transportation system in a data-driven way.
Previously, I worked as Deputy Director of R&D at Sensetime Technology Ltd, leading a product team containing over 30 talented engineers and product specialists, developing the RoboX Autonomous Products, including RoboBus & RoboSweeper.
I obtained my Ph.D. from The Chinese University of Hong Kong in May, 2020 supervised by Prof. Xiaogang Wang and Prof. Xiaoou Tang. I got my bachelor’s degrees of Electronic Engineering and Economics in Tsinghua University in 2016. I worked as an research intern at Microsoft Research Asia (MSRA) and Facebook Reality Labs(Now Meta Reality Labs) during my Ph.D. years.
Research interest: 3D Scene Reconstruction, 3D Scene Perception, Behavior & Scene Simulation, any Autonomous-Driving-related topic.
***Important*** Our team is searching for highly self-motivated interns / full-time employees / post-docs . If you are interested in solving the industrial problem in an academic way, do not hesitate to contact me.
News
Jul 4, 2022
Two papers are accepted by ECCV-2022, sensor fusion * 1 and NeRF * 1.
NEW!
Jul 1, 2022
I have finished all the handovers at Sensetime. I am really grateful for the 3-year unforgettable experience here.
Jun 30, 2022
Two autonomous-driving-related papers got accepted, ITS-C * 1 and IROS * 1.
May 27, 2022
Our Calibration Toolbox for Autonomous Driving, OpenCalib (Code and Paper), is now released.
Mar 22, 2022
The group standard for RoboBus led by us is released. 《自动驾驶小型客车总体技术要求》
Mar 2, 2022
Two papers are accepted by CVPR-2022, poster * 1 and oral * 1.
Selected publications
Conferences
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
@inproceedings{li2022ltracing,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={European Conference on Computer Vision},year={2022},bibtex_show={true},abbr={ECCV},corr={false},selected={true}}
ECCV
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
Xin Li,
Botian Shi,
Yuenan Hou,
Xingjiao Wu,
Tianlong Ma,
Yikang Li#
,
and Liang He
@inproceedings{li2022hmfi,title={Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection},author={Li, Xin and Shi, Botian and Hou, Yuenan and Wu, Xingjiao and Ma, Tianlong and Li, Yikang and He, Liang},booktitle={European Conference on Computer Vision},year={2022},bibtex_show={true},abbr={ECCV},corr={true},selected={true}}
IROS
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene
Pengjin Wei,
Guohang Yan,
Yikang Li
,
Kun Fang,
Wei Liu,
Xinyu Cai,
and Jie Yang
International Conference on Intelligent Robots and Systems
2022
@inproceedings{li2022calib,title={CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road Scene},author={Wei, Pengjin and Yan, Guohang and Li, Yikang and Fang, Kun and Liu, Wei and Cai, Xinyu and Yang, Jie},booktitle={International Conference on Intelligent Robots and Systems},year={2022},bibtex_show={true},abbr={IROS},corr={false},selected={true}}
ITSC
General Driving Behavior Model based on the Desired Safety Margin for Vehicle Flow Simulation
Pinlong Cai,
Junjie Zhang,
Xuan Zhao,
and Yikang Li#
International Conference on Intelligent Transportation Systems
2022
@inproceedings{li2022sim,title={General Driving Behavior Model based on the Desired Safety Margin for Vehicle Flow Simulation},author={Cai, Pinlong and Zhang, Junjie and Zhao, Xuan and Li, Yikang},booktitle={International Conference on Intelligent Transportation Systems},year={2022},bibtex_show={true},abbr={ITSC},corr={true},selected={true}}
CVPR
β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Peng Ye,
Baopu Li,
Yikang Li
,
Tao Chen,
Jiayuan Fan,
and Wanli Ouyang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2022
@inproceedings{li2022betadecay,title={$\beta $-DARTS: Beta-Decay Regularization for Differentiable Architecture Search},author={Ye, Peng and Li, Baopu and Li, Yikang and Chen, Tao and Fan, Jiayuan and Ouyang, Wanli},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},year={2022},bibtex_show={true},abbr={CVPR},corr={false},arxiv={https://arxiv.org/abs/2203.01665},pdf={https://arxiv.org/pdf/2203.01665},selected={true}}
CVPR
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
@inproceedings{li2022lidarsegkd,title={Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation},author={Hou, Yuenan and Zhu, Xinge and Ma, Yuexin and Loy, Chen Change and Li, Yikang},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},year={2022},bibtex_show={true},abbr={CVPR},selected={true},corr={true},arxiv={https://arxiv.org/abs/2206.02099},pdf={https://arxiv.org/pdf/2206.02099},code={https://github.com/cardwing/Codes-for-PVKD}}
NeurIPS
Pastegan: A Semi-parametric Method to Generate Image from Scene Graph
Yikang Li
,
Tao Ma,
Yeqi Bai,
Nan Duan,
Sining Wei,
and Xiaogang Wang
Advances in Neural Information Processing Systems (NeurIPS)
2019
@inproceedings{li2019pastegan,title={Pastegan: A Semi-parametric Method to Generate Image from Scene Graph},author={Li, Yikang and Ma, Tao and Bai, Yeqi and Duan, Nan and Wei, Sining and Wang, Xiaogang},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},volume={32},year={2019},bibtex_show={true},abbr={NeurIPS},arxiv={https://arxiv.org/abs/1709.07192},pdf={https://proceedings.neurips.cc/paper/2019/file/12b1e42dc0746f22cf361267de07073f-Paper.pdf},poster={assets/files/publications/nips19_pastegan_poster.pdf},code={https://github.com/yikang-li/PasteGAN},selected={true}}
ECCV
Factorizable Net: an Efficient Subgraph-based Framework for Scene Graph Generation
Yikang Li
,
Wanli Ouyang,
Bolei Zhou,
Jianping Shi,
Chao Zhang,
and Xiaogang Wang
Proceedings of the European Conference on Computer Vision (ECCV)
2018
@inproceedings{li2018fnet,title={Factorizable Net: an Efficient Subgraph-based Framework for Scene Graph Generation},author={Li, Yikang and Ouyang, Wanli and Zhou, Bolei and Shi, Jianping and Zhang, Chao and Wang, Xiaogang},booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},pages={335--351},year={2018},bibtex_show={true},abbr={ECCV},arxiv={https://arxiv.org/abs/1806.11538},pdf={assets/files/publications/eccv18_fnet.pdf},poster={assets/files/publications/eccv18_fnet_poster.pdf},code={https://github.com/yikang-li/FactorizableNet},selected={true}}
CVPR
Visual Question Generation as Dual Task of Visual Question Answering
Yikang Li
,
Nan Duan,
Bolei Zhou,
Xiao Chu,
Wanli Ouyang,
Xiaogang Wang,
and Ming Zhou
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2018
@inproceedings{li2018iqan,title={Visual Question Generation as Dual Task of Visual Question Answering},author={Li, Yikang and Duan, Nan and Zhou, Bolei and Chu, Xiao and Ouyang, Wanli and Wang, Xiaogang and Zhou, Ming},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},pages={6116--6124},year={2018},bibtex_show={true},abbr={CVPR},arxiv={https://arxiv.org/abs/1709.07192},pdf={assets/files/publications/cvpr18_iqan.pdf},poster={assets/files/publications/cvpr18_iqan_poster.pdf},code={https://github.com/yikang-li/iQAN},selected={true}}
ICCV
Scene Graph Generation from Objects, Phrases and Region Captions
Yikang Li
,
Wanli Ouyang,
Bolei Zhou,
Kun Wang,
and Xiaogang Wang
Proceedings of the IEEE International Conference on Computer Vision (ICCV)
2017
@inproceedings{li2017scene,title={Scene Graph Generation from Objects, Phrases and Region Captions},author={Li, Yikang and Ouyang, Wanli and Zhou, Bolei and Wang, Kun and Wang, Xiaogang},booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)},pages={1261--1270},year={2017},bibtex_show={true},abbr={ICCV},arxiv={https://arxiv.org/abs/1707.09700},pdf={assets/files/publications/iccv17_msdn.pdf},poster={assets/files/publications/iccv17_msdn_poster.pdf},code={https://github.com/yikang-li/MSDN},selected={true}}
@inproceedings{li2017vip,title={ViP-CNN: Visual Phrase Guided Convolutional Neural Network},author={Li, Yikang and Ouyang, Wanli and Wang, Xiaogang},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},pages={1347--1356},year={2017},bibtex_show={true},abbr={CVPR},arxiv={https://arxiv.org/abs/1702.07191},pdf={assets/files/publications/cvpr17_vip_cnn.pdf},poster={assets/files/publications/cvpr17_vip_cnn_poster.pdf},selected={true}}
Preprints
Arxiv
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
Guohang Yan,
Zhuochun Liu,
Chengjie Wang,
Chunlei Shi,
Pengjin Wei,
Xinyu Cai,
Tao Ma,
Zhizheng Liu,
Zebin Zhong,
Yuqian Liu,
Ming Zhao,
Zheng Ma,
and Yikang Li#
@article{opencalib,title={OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving},author={Yan, Guohang and Liu, Zhuochun and Wang, Chengjie and Shi, Chunlei and Wei, Pengjin and Cai, Xinyu and Ma, Tao and Liu, Zhizheng and Zhong, Zebin and Liu, Yuqian and Zhao, Ming and Ma, Zheng and Li, Yikang},journal={arXiv preprint arXiv:2205.14087},year={2022},abbr={Arxiv},arxiv={https://arxiv.org/abs/2205.14087},pdf={https://arxiv.org/pdf/2205.14087},bibtex_show={true},corr={true},selected={true},code={https://github.com/PJLab-ADG/SensorsCalibration}}
Arxiv
Joint Camera Intrinsic and LiDAR-Camera Extrinsic Calibration
@article{yan2022joint,title={Joint Camera Intrinsic and LiDAR-Camera Extrinsic Calibration},author={Yan, Guohang and He, Feiyu and Shi, Chunlei and Cai, Xinyu and Li, Yikang},journal={arXiv preprint arXiv:2202.13708},year={2022},abbr={Arxiv},arxiv={https://arxiv.org/abs/2202.13708},pdf={https://arxiv.org/pdf/2202.13708},bibtex_show={true},corr={true},selected={true},code={https://github.com/OpenCalib/JointCalib}}
Arxiv
Multi-modal Sensor Fusion for Auto Driving Perception: A Survey
Keli Huang,
Botian Shi,
Xiang Li,
Xin Li,
Siyuan Huang,
and Yikang Li#
@article{huang2022multi,title={Multi-modal Sensor Fusion for Auto Driving Perception: A Survey},author={Huang, Keli and Shi, Botian and Li, Xiang and Li, Xin and Huang, Siyuan and Li, Yikang},journal={arXiv preprint arXiv:2202.02703},year={2022},abbr={Arxiv},arxiv={https://arxiv.org/abs/2202.02703},pdf={https://arxiv.org/pdf/2202.02703},bibtex_show={true},corr={true},selected={true}}
Arxiv
Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design
@article{ma2021pe,title={Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design},author={Ma, Tao and Liu, Zhizheng and Li, Yikang},journal={arXiv preprint arXiv:2104.06615},year={2021},abbr={Arxiv},arxiv={https://arxiv.org/abs/2104.06615},pdf={https://arxiv.org/pdf/2104.06615},bibtex_show={true},corr={true},selected={true}}
Arxiv
CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes
@article{ma2021crlf,title={CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes},author={Ma, Tao and Liu, Zhizheng and Yan, Guohang and Li, Yikang},journal={arXiv preprint arXiv:2103.04558},year={2021},abbr={Arxiv},arxiv={https://arxiv.org/abs/2103.04558},pdf={https://arxiv.org/pdf/2103.04558},code={https://github.com/PJLab-ADG/SensorsCalibration},bibtex_show={true},corr={true},selected={true}}
Please contact me via email: liyikang@pjlab.org.cn