Peng YUN
I got my Ph.D. degree in 2023.01 from the Hong Kong University of Science and Technology, supervised by Prof. Ming LIU in RAM-Lab . I received my bachelor degree in 2017 from Huazhong University of Science and Technology. I joined HKUST RoboCup as a team member in 2017. Since then, I started my robotic work.
Email  / 
Google Scholar  / 
CV
Research
My research interests include 3D object detection, incremental learning, Bayesian neural networks, uncertainty estimation, and autonomous driving applications. Representative papers are highlighted .
Accurate and robust visual localization system in large-scale appearance-changing environments
IEEE/ASME Transactions on Mechatronics , 2022
Yang Yu, Peng Yun , Bohuan Xue, Jianhao Jiao, Rui Fan, Ming Liu
pdf /
bibtex
Laplace Approximation Based Epistemic Uncertainty Estimation in 3D Object Detection
Conference on Robotic Learning , 2022
Peng Yun , Ming Liu
pdf /
bibtex /
video
Open-world semantic segmentation for lidar point clouds
ECCV 2022
Jun Cen, Peng Yun , Shiwei Zhang, Junhao Cai, Di Luan, Mingqian Tang, Ming Liu, Michael Yu Wang
pdf /
bibtex /
code /
video
Open-set 3D object detection
International Conference on 3D Vision (3DV), 2021
Jun Cen, Peng Yun , Junhao Cai, Michael Yu Wang, Ming Liu
pdf /
bibtex
Conflicts between likelihood and knowledge distillation in task incremental learning for 3d object detection
International Conference on 3D Vision (3DV) , 2021
Peng Yun , Jun Cen, Ming Liu
pdf /
bibtex /
video
Deep metric learning for open world semantic segmentation
IEEE/CVF International Conference on Computer Vision, 2021
Jun Cen, Peng Yun , Junhao Cai, Michael Yu Wang, Ming Liu
pdf /
bibtex
FuseSeg: Semantic Segmentation of Urban Scenes Based on RGB and Thermal Data Fusion
IEEE Transactions on Automation Science and Engineering (T-ASE) , 2020
Yuxiang Sun, Weixun Zuo, Peng Yun , Hengli Wang, Ming Liu
pdf /
bibtex /
video
In Defense of Knowledge Distillation for Task Incremental Learning and Its Application in 3D Object Detection.
RAL, 2021
Peng Yun* ,
Yuxuan Liu,
Ming Liu
pdf /
bibtex /
project page /
code
MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving.
IROS, 2020
Jianhao Jiao*,
Peng Yun* ,
Yuying Chen,
Congcong Liu,
Haoyang Ye,
Ming Liu (* indicates equal contribution)
pdf /
bibtex /
video /
code /
dataset
Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective.
IROS, 2019
Lei Tai,
Peng Yun ,
Yuying Chen,
Congcong Liu,
Haoyang Ye,
Ming Liu
pdf /
bibtex /
video /
code
Focal Loss in 3D Object Detection.
IEEE Robotics and Automation Letters (RA-L), 2019
ICRA, 2019
Peng Yun ,
Lei Tai,
Yuan Wang,
Chengju Liu,
Ming Liu
pdf /
bibtex /
page /
code
VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control.
IEEE Robotics and Automation Letters (RA-L), 2019
Jingwei Zhang*,
Lei Tai*,
Peng Yun ,
Yufeng Xiong,
Ming Liu,
Joschka Boedecker,
Wolfram Burgard
(*indicates equal contribution)
pdf /
bibtex /
supplement /
page /
video
Pointseg: Real-time semantic segmentation based on 3d lidar point cloud.
arXiv preprint arXiv:1807.06288
Yuan Wang,
Tianyue Shi,
Peng Yun ,
Lei Tai,
Ming Liu
pdf /
bibtex /
code
Towards a Cloud Robotics Platform for Distributed Visual SLAM.
International Conference on Computer Vision Systems (ICVS), 2017
Peng Yun ,
Jianhao Jiao,
Ming Liu
pdf /
bibtex
A Cloud-Based Visual SLAM framework for Low-Cost Agents, International Conference on Computer Vision Systems.
International Conference on Computer Vision Systems (ICVS), 2017
Jianhao Jiao,
Peng Yun ,
Ming Liu
pdf /
bibtex
Demo
There are some demos for 3D object detection of some work in progress. Just for visulization. :)
Your browser does not support the video tag.