Qiyu Dai 戴启宇

I am a second-year Ph.D Student in Intelligent Science and Technology at Peking University, supervised by Prof. Baoquan Chen. Before that, I received my M.Eng. from Peking University, supervised by Prof. He Wang and Prof. Qi Jing, and Bachelor from Wuhan University. I am also privileged to work closely with Prof. Wenzheng Chen, Prof. Mengyu Chu, Prof. Pengshuai Wang at Peking University.

Email  /  Google Scholar  /  CV

profile photo profile photo hover

Research

I work at the intersection of 3D Computer Vision and Computer Graphics. My goal is to develop intelligent systems that can perceive, understand, and generate dynamic, physical 3D worlds, facilitating next-generation AR/VR and AI glasses. Currently, I am working towards building controllable, generative world simulators that enable realistic interaction with humans. I am also interested in 3D/4D reconstruction and generation, neural rendering, and spatial understanding.

* Equal contribution, † Corresponding author

Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding
Jiaheng Li*, Qiyu Dai*, Lihan Li, Praneeth Chakravarthula, He Sun, Baoquan Chen†, Wenzheng Chen†
ACM SIGGRAPH Asia Conference Papers, 2025
project page / paper

RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting
Qiyu Dai*, Xingyu Ni*, Qianfan Shen, Wenzheng Chen†, Baoquan Chen†, Mengyu Chu†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Top 3 Paper Award & Best Technique Honorable Mention @ China3DV 2025
project page / paper

One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency
Li Jin, Yujie Wang, Wenzheng Chen, Qiyu Dai, Qingzhe Gao, Xueyin Qin, Baoquan Chen†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Highlight
project page / paper

4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
Yuanxing Duan*, Fangyin Wei*, Qiyu Dai, Yuhang He, Wenzheng Chen†, Baoquan Chen†
ACM SIGGRAPH Conference Papers, 2024
project page / paper

Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach
Yufei Ding*, Haoran Geng*, Chaoyi Xu, Xiaomeng Fang, Jiazhao Zhang, Songlin Wei, Qiyu Dai, Zhizheng Zhang, He Wang†
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
Oral Presentation
project page / paper

STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines
Yuxuan Kuang*, Qin Han*, Danshi Li, Qiyu Dai, Lian Ding, Dong Sun, Hanlin Zhao, He Wang†
IEEE International Conference on Robotics and Automation (ICRA), 2024
Oral Presentation
project page / paper

GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF
Qiyu Dai*, Yan Zhu*, Yiran Geng, Ciyu Ruan, Jiazhao Zhang, He Wang†
IEEE International Conference on Robotics and Automation (ICRA), 2023
project page / paper

Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Qiyu Dai*, Jiyao Zhang*, Qiwei Li, Tianhao Wu, Hao Dong, Ziyuan Liu, Ping Tan, He Wang†
European Conference on Computer Vision (ECCV), 2022
Origin of GALBOT's Sim-to-Real Paradigm for Robot Training
project page / paper

Edit Like A Designer: Modeling Design Workflows for Unaligned Fashion Editing
Qiyu Dai, Shuai Yang, Wenjing Wang, Wei Xiang, Jiaying Liu†
ACM International Conference on Multimedia (ACM MM), 2021
paper

Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks
Qin Zou, Hanwen Jiang, Qiyu Dai, Yuanhao Yue, Long Chen, Qian Wang†
IEEE Transactions on Vehicular Technology, 2020
IEEE Best Land Transportation Paper Award
project page / paper

Education

Peking University, China Sept. 2024 - Present
Ph.D Student in Intelligent Science and Technology, School of Intelligent Science and Technology
Advisor: Prof. Baoquan Chen

Peking University, China Sept. 2019 - Jun. 2022
M.Eng. in Computer Technology, School of Software and Microelectronics
Advisor: Prof. He Wang, Prof. Qi Jing

Wuhan University, China Sept. 2015 - Jun. 2019
B.Eng. in Energy Chemical Engineering, School of Power and Mechanical Engineering
Second B.Sc. in Computer Science, School of Computer Science
Advisor: Prof. Qin Zou

Selected Experience

Research Intern, ByteDance Seed Apr. 2025 - Oct. 2025
Mentor: Yongjie Zhang

Research Assistant, Visual Computing and Learning (VCL) Lab @ PKU Jun. 2023 - Sept. 2024
Mentor: Prof. Baoquan Chen

Research Intern, Beijing Academy of Artificial Intelligence (BAAI) Nov. 2022 - Jun. 2023
Mentor: Prof. He Wang

Research Assistant, Embodied Perception and InteraCtion (EPIC) Lab @ PKU Mar. 2021 - Jun. 2023
Mentor: Prof. He Wang

Services

Conference Reviewer: CVPR, ECCV, ICCV, NeurIPS, AAAI, ICRA, IROS, RSS SemRob, CAD/Graphics

Journal Reviewer: SIGGRAPH, IEEE TCSVT, IEEE RA-L

Invited Talks

Physics-based Open-World Rain Synthesis
Shandong University Apr. 2025
Huawei Cloud Dec. 2024

Enhancing Gaussian Splatting with Dynamics
Tsinghua AGI Seminar Jan. 2025

Depth Simulation and Restoration for Specular and Transparent Objects
ECCV Pre-Workshop, China Society of Image and Graphics (CSIG) Aug. 2022

Awards and Honors

NeurIPS Top Reviewer 2025

IEEE Best Land Transportation Paper Award, IEEE Vehicular Technology Society 2025

Top 3 Paper Award, China3DV 2025

Best Technique Honorable Mention, China3DV 2025

Outstanding Master's Thesis, Peking University 2022

Merit Student Award, Peking University 2020, 2025

Social Work Award, Peking University 2021

Excellent Bachelor Graduate, Wuhan University 2019

Merit Student & Excellent Student Award, Wuhan University 2016, 2017, 2018

Scholarships: Shaosi Scholarship (2025), Excellent Student Scholarship (Wuhan University, 2016, 2017, 2018), Beijing CM Scholarship (2018), Goaland Scholarship (2017), Cnhili Scholarship (2016), Relations Instruments Scholarship (2016)


Thanks to Jon Barron for the template.
Last updated: Dec. 11, 2025