Home             Publications             Projects             Experience             Contact

Rong Li       李 蓉  

I am a Research Assistant at The Hong Kong University of Science and Technology(Guangzhou), working with Prof. Junwei Liang.

Previously, I collaborated with Anh-Quan Cao and Dr. Raoul de Charette from Inria. I workded was an intern with Zhuangwei Zhuang of Pazhou Lab under the supervision of Prof. Dr. Mingkui Tan.

My current research is focused on 3D scene perception, multi-sensor fusion and data-efficient learning.

Google Scholar    GitHub


TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation

Rong Li, Shijie Li, Xieyuanli Chen, Teli Ma, Hao Wang, Juergen Gall. Junwei Liang.
arXiv Preprint, 2023

An Examination of the Compositionality of Large Generative Vision-Language Models

Teli Ma, Rong Li, Junwei Liang.
arXiv Preprint, 2023
Paper Project

Semantic RGB-D Image Synthesis (Oral)

Shijie Li, Rong Li, Juergen Gall.
International Conference on Computer Vision workshop, 2023

Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation

Rong Li, Anh-Quan Cao, Raoul de Charette.
The British Machine Vision Conference, 2022
Paper Code Poster Slides Video

Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation

Zhuangwei Zhuang, Rong Li, Yuanqing Li, Kui Jia, Qicheng Wang, Mingkui Tan.
International Conference on Computer Vision, 2021
Paper Code Slides Video


SensatUrban: Urban-Scale Point Clouds Understanding (ICCV 2021 Challenge)

is a BEV multi-sensor-fusion-based point cloud semantic segmentation implementation. Collaborated with Zhuangwei Zhuang. Ranked 5-th.
Code Board

An Embedded Mobile Platform Equipped with LiDAR and Camera

is an embedded mobile platform equipped with Livox LiDAR and Camera and is developed on Nvidia Jetson Xavier NX. Developed ith Zhuangwei Zhuang.
Video Code Slides

Human Segmentation for Intelligence Education

aims to reappear the obscured content on the blackboard by teacher to improve the quality of online courses. Collaborated with Zhuoman Liu, Gang Dai, Jiaqiu Zhou.

Deep View Synthesis via Self-Consistent Generative Network

aims to synthesize the front view from left and right views. Coolabrate with Zhuoman Liu and etc.
Code Video Dataset


[2022.11 - now]             Research Assistant, HKUST(GZ), Precognition Group, China

[2021.12 - 2022.07]      Research Assistant, Inria, ASTRA Team, France

[2020.10 - 2021.09]      Algorithm Intern, Pazhou Lab, China

[2018.10 - 2019.06]      Algorithm Intern, CVTE Research, China


[2019 - 2022]      M.Sc., South China University of Technology

[2015 - 2019]      B.Sc., South China University of Technology


Reviewer:   BMVC2023


Email:      lirong0329 at qq.com