Zhiqi Li

Zhiqi Li (李志琦)
Affiliation: CS Department, Nanjing University
Address: 163 XIANLIN ROAD, QIXIA DISTRICT, NANJING, JIANGSU PROVINCE
Email: lzq[at]smail.nju.edu.cn

About Me ([GitHub] [Google Scholar]

I am a Ph.D. candidate at Nanjing University, supervised by Prof.Tong Lu. Previously, I obtained the bachelor degree from Department of Computer Science and Technology, Nanjing University (NJU) in 2020.

Currently, I am mainly working on Vision-Language Model at NVIDIA. I developed the well-known BEVFormer and won the champoins of Waymo 3D Camera-Only Detection Challenge on CVPR2022 and Occupancy Prediction Challenge on CVPR2023.

I am actively seeking research opportunities in the industry or postdoctoral positions in academia for 2025.

News

2024/02: BEV-Planner and DCNv4 were accepted at CVPR'24.
2023/11: VCD was accepted at NeurIPS'23 and our BEV surery is accepted to TPAMI.
2023/10: InternImage is selected as one of CVPR 2023 Top-10 Influential Papers.
2023/07: FB-BEV was accepted at ICCV'23.
2023/06: Our team wins both the outstanding champion and Innovation Award of Occupancy Prediction Challenge (15,000+5,000 UDS Bonus) on CVPR2023.
2023/01: BEVFormer is selected as one of ECCV 2022 Top-10 Influential Papers and the 100 most cited AI papers in 2022.
2022/11: We release InternImage, setting a new record 65.4 box mAP on COCO test-dev.
2022/06: Our team wins the champion of Waymo 2022 3D Camera-Only Detection Task (15,000 USD Bonus).

Experience

2023 - 2024: Research Intern at Shanghai AI Laboratory, led by Prof. Jifeng Dai and Wenhai Wang
2022 - 2023: Research Intern at NVIDIA, led by Jose M. Alvarez and Zhiding Yu
2021 - 2022: Research Intern at Shanghai AI Laboratory, led by Prof. Jifeng Dai and Wenhai Wang

Recent Works ([Full List])

(* Equal contribution, # Corresponding authors)

FB-BEV: BEV Representation from Forward-Backward View Transformations
Zhiqi Li, Zhiding Yu, Wenhai Wang, Anima Anandkumar, Tong Lu, Jose M. Alvarez
ICCV, 2023
[Paper] [Code]

[BibTex]
Forward-Backward View Transformation

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wenhai Wang*, Jifeng Dai*, Zhe Chen*†, Zhenhang Huang* Zhiqi Li*†, Xizhou Zhu*, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, Xiaogang Wang, Yu Qiao#
CVPR, 2023 (Highlight Paper (2.5%))
[Paper] [Code]
[CVPR 2023' Top-10 Influential Papers]

[BibTex]
A strong large-scale CNN-based fondamention model.

BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
Zhiqi Li*†, Wenhai Wang*, Hongyang Li*, Enze Xie, Chonghao Sima, Tong Lu, Yu Qiao, Jifeng Dai#
ECCV, 2022
[Paper] [Code]

[BibTex]
[ECCV 2022' Top-10 Influential Papers]
[100 Most Cited AI Papers in 2022]
A versatile camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
Zhiqi Li, Wenhai Wang#, Enze Xie, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Tong Lu#, Ping Luo
CVPR, 2022
[Paper] [Code]

[BibTex]
A unified segmentation framework.

Technical Report

FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation
Zhiqi Li, Zhiding Yu, David Austin, Mingsheng Fang, Shiyi Lan, Jan Kautz, Jose M. Alvarez

[Paper] [Code]

[BibTex]
Best Champion of CVPR2023 Occupancy Prediction Challenge.

Honors and Awards

2023/12: NVIDIA Graduate Fellowship (Top-10 globally, First awarded student from Chinese institution)
2023/12: Distinguished Student of Nanjing University (南京大学学生年度人物, Top-10)
2023/11: National Scholarship
2023/06: Occupancy Prediction Challenge, 1st Place and Innovation Award (15,000+5000 USD Bonus)
2022/06: Waymo 2022 3D Camera-Only Detection Task, 1st Place (15,000 USD Bonus)

Review Services

Journal Reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)

Program Committee Member/Conference Reviewer
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 2024
Neural Information Processing Systems (NeurIPS), 2023
IEEE International Conference on Computer Vision (ICCV), 2023
AAAI Conference on Artificial Intelligence (AAAI), 2023, 2024
ICLR, 2023

Friends

Zhe Chen, Guo Chen