Mingjie Pan

Mingjie Pan (潘铭杰)
Affiliation: Peking University
Address: 5 Yiheyuan Road, Haidian District, Beijing, China
Email: pmj@stu.pku.edu.cn

About Me ([GitHub] [Google Scholar] )

I'm currently a Master student at the Peking University (PKU).

Previously, I received my B.E degree from University of Electronic Science and Technology (UESTC).

My research interests focus on:

3D Vision & Embodied AI
Domain Adptation
Unsupervised Learning

News

2024/01: One paper is accepted by ICRA 2024.
2023/12: One paper is accepted by AAAI 2024.
2023/09: Ranked 2nd place in ICCV 2023 Challenge - Continual Test-time Adaptation for Semantic Segmentation.
2023/06: One paper is selected by MICCAI 2023.
2023/05: Ranked 3rd place in CVPR 2023 Challenge - Vision-Centric 3D Occupancy Prediction.
2023/03: One paper is selected by CVPR 2023.
2020/06: Win Finalist Award in MCM/ICM 2020. (Top 0.5%)
2020-06: Win National First Prize in RoboMaster 2020.

Experience

2023/04 - Present: Engineering Intern at Xiaomi Car, responsible for tasks such as Occupancy Prediction and Autolabeling in autonomous driving.
2022/10 - 2023/04: Research Assistant at the Peking University (PKU), led by Prof. Shanghang Zhang
2022/06 - 2022/08: Research Intern at Huawei, led by Dr. Yihang Lou
2021/10 - 2022/05: Engineering Intern at Megvii, responsible for tasks such as 3D detection and depth estimation in autonomous driving.

Research

(* Equal contribution)

RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
Mingjie Pan*, Jiaming Liu*, Renrui Zhang*, Peixiang Huang, Xiaoqi Li, Bing Wang, Hongwei Xie, Li Liu, Shanghang Zhang
ICRA, 2024, Code
We propose a universal 3D occupancy training paradigm that leverage 2D labels.

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding
Senqiao Yang*, Jiaming Liu*, Ray Zhang*, Mingjie Pan*, Zoey Guo, Xiaoqi Li, Zehui Chen, Peng Gao, Yandong Guo, Shanghang Zhang
AAAI, 2025

UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
Mingjie Pan, Li Liu, Jiaming Liu, Peixiang Huang, Longlong Wang, Shanghang Zhang, Kuiyuan Yang
3rd place of CVPR 2023 Challenge - Vision-Centric 3D Occupancy Prediction
Technical Report, 2023

DiffuseIR: Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
Mingjie Pan*, Yulu Gan*, Fangxu Zhou, Jiaming Liu, Ying Zhang, Aimin Wang, Shanghang Zhang, Dawei Li
MICCAI, 2023

An unsupervised and strong isotropic reconstruction method based on diffusion models.

Exploring sparse visual prompt for cross-domain semantic segmentation
Senqiao Yang*, Jiarui Wu*, Jiaming Liu, Xiaoqi Li, Qizhe Zhang, Mingjie Pan, Shanghang Zhang
AAAI, 2024

Utilize visual prompts for domain adaptation in semantic segmentation tasks.

Cloud-device collaborative adaptation to continual changing environments in the real-world
Yulu Gan*, Mingjie Pan*, Rongyu Zhang, Zijian Ling, Lingran Zhao, Jiaming Liu, Shanghang Zhang
CVPR, 2023

A cloud-device collaborative framework that helps device models adapt to continuously changing environments.

Selected Awards

3rd Prize of CVPR 2023 Challenge - Vision-Centric 3D Occupancy Prediction, May 2023 (Team leader)
Silver medal (12th/1506) at Kaggle, Sartorius - Cell Instance Segmentation, Apr 2022 (Team leader)
Finalist Award (Top 0.5% of 27149) at MCM/ICM, June 2020 (Team leader)
1st Prize at RoboMaster, Mainland China Regional Competition, June 2020 (Team leader)
2nd Prize at National Undergraduate Electronic Design Contest, Automatic quadcopter, Sept 2019 (Team leader)
Outstanding Graduate Special Scholarship (x2), 2018 - 2019

MISC

Experience of robots from years ago.