|
|
|
I am currently pursuing a second M.Sc. in Electrical Engineering and Information Technology at the Technical University of Munich. At TUM, I am working on my master's thesis on human motion video diffusion with Yu Chi, Jiapeng Tang, and Prof. Matthias NieĂźner at the TUM Visual Computing Group. In parallel, I am an intern at Agile Robots SE, where I work with Mahdi Hamad on video-action world models for robot dexterous manipulation. My previous research and industry experience includes a research internship at TUM Visual Computing with Jiapeng Tang and Prof. Matthias NieĂźner, a working student position at ImFusion with Mert Asim Karaoglu, Prof. Benjamin Busam, Prof. Nassir Navab, as well as research at TUM-CVG and Oxford VGG with Prof. Daniel Cremers, Prof. Yan Xia, Prof. Chuanxia Zheng and Weirong Chen. I also completed a research internship at Zhejiang University under the supervision of Prof. Yiyi Liao. Before joining TUM, I earned an M.Sc. in Computer Science from Tongji University and a B.Sc. in Information and Computing Science from Nanjing Tech University. |
Seeking Ph.D. opportunities for Fall 2027 entry |
|
|
|
|
10/2025
Our paper CSG-Fusion received the 🏆 Best Paper Award at the ICCV 2025 Workshop E2E3D. 08/2025
Our paper CSG-Fusion is accepted by ICCV 2025 Workshop E2E3D. 07/2025
I graduated from Tongji University with a Master's degree in Computer Science. 🎓 06/2025
Our paper LiteTracker is accepted by MICCAI 2025. 01/2025
Our paper Re0 is accepted by ICRA 2025. 08/2024
I will join Imfusion as a working student on the topic of Dense Video Point Tracking. 01/2024
I will join TUM-CVG, TUM-DI-LAB under the co-supervision of Dr. Yan Xia and Dr. Chuanxia Zheng. 05/2023
I will join Technische University München in the winter semester 23/24 as a Master student in Electrical Engineering, see you in München🍻! |
|
Thoughts on research, 3D, video generation, and the occasional in-between. Loading blog posts...
|
|
My research interests focus on moving beyond isolated visual subproblems toward integrated models of virtual humans and 3D scenes that can perceive, generate, and reason about interaction in dynamic environments.
Integrative Direction
Perception-Action World Models
Bridging geometry, generation, tracking, and interaction into a single modeling direction. |
|
* equal contribution, †corresponding author |
|
Authors Overview A feed-forward framework that mindfully integrates pixel-aligned pointmap to reduce redundant primitives and produce compact and consistent 3D structures. |
|
Authors Overview A low-latency method for tissue online tracking in endoscopic video streams, introduces a set of training-free runtime optimizations on a state-of-the-art long-term point tracking method. |
|
Authors Overview Given 3D point clouds and multi-view RGB-D images with poses, Re0 leverages the 3D geometric information, projection relationships and CLIP semantic features for 3D zero-shot instance segmentation. |
|
|
|
|
Master's Thesis
3D/4D Reconstruction
Overview Given stereo endoscopic videos of deformable tissues, this thesis proposes a 4D deformable half-Gaussian splatting framework with depth-prior initialization, temporal–spatial encoding, and lightweight Gaussian pruning for high-fidelity, real-time surgical scene reconstruction. |
|
|
|
Internship
Perception-Action World Models
Mentors
Mahdi Hamad
Agile Robots SE
|
|
Master Thesis
Mentors
Yu Chi,
Jiapeng Tang,
Prof. Matthias NieĂźner
TUM Visual Computing
|
|
|
Research Internship
Mentors
Jiapeng Tang,
Prof. Matthias NieĂźner
TUM Visual Computing
|
|
Research Internship
Long-term Tracking
Mentors
Mert Asim Karaoglu
Imfusion & TUM CAMP
Prof. Benjamin Busam,
Prof. Nassir Navab
TUM CAMP
Dr. Alexander Ladikos
Imfusion
|
|
Guided Research
Mentors
Prof. Daniel Cremers,
Prof. Yan Xia,
Weirong Chen
TUM CVG
Prof. Chuanxia Zheng
Oxford VGG
|
|
Research Assistant
3D/4D Reconstruction
Mentors
Prof. Yiyi Liao
Zhejiang University
|
|
|
|
Personal Project
Focus Reusable User Study Infrastructure Overview An open-source toolkit for building reusable user study questionnaires and experiment workflows. |
|
Personal Project
Focus 2D Audio-driven Human Avatar Animation Overview A lightweight audio-driven 2D avatar solution that runs entirely in the browser using WASM based on Lite-avatar. No backend server required. |
|
|
|
|
Education
M.Sc.
Program Electrical Engineering and Information Technology |
|
|
Education
M.Sc.
Program Computer Science |
|
|
Education
B.Sc.
Program Information and Computing Science (Embedded Software) |
|
|
| 2023 - 2024 Munich, Germany |
Recognition
|
| 2019 - 2020 Nanjing, China |
Recognition
|
                       
Interactive Thermal Receipt Simulation
Receipt Deformation Simulation
Three.js + WebGL + Verlet Cloth
Duck Pool: Interactive Water Simulation
Dive into an interactive water simulation where ducks float, collide, and create ripples.
Three.js + CPU Simulation
|
|
|
| Last Updated on 2026/04/26 |
|
|
