About Wenbo Ji

Wenbo Ji is a master's student and researcher in visual computing, generative modeling, and robotics. He is currently pursuing a second M.Sc. in Electrical Engineering and Information Technology at the Technical University of Munich, where his work connects human motion video diffusion, 3D scene understanding, video-action world models, and robot dexterous manipulation.

Current work

At the TUM Visual Computing Group, Wenbo is working on his master's thesis on human motion video diffusion with Yu Chi, Jiapeng Tang, and Prof. Matthias Nießner. In parallel, he is an intern at Agile Robots SE, working with Mahdi Hamad on video-action world models for robot dexterous manipulation.

The common thread is interaction: models that do not only recognize isolated visual patterns, but can generate, predict, and reason about humans, objects, scenes, and actions over time.

Previous experience

Wenbo's previous research and industry experience includes a research internship at TUM Visual Computing with Jiapeng Tang and Prof. Matthias Nießner, and a working student position at ImFusion with Mert Asim Karaoglu, Prof. Benjamin Busam, and Prof. Nassir Navab.

He has also worked on computer vision research at TUM-CVG and Oxford VGG with Prof. Daniel Cremers, Prof. Yan Xia, Prof. Chuanxia Zheng, and Weirong Chen. Earlier, he completed a research internship at Zhejiang University under the supervision of Prof. Yiyi Liao.

Research interests

Wenbo's research interests focus on integrated models for virtual humans, 3D scenes, and embodied agents. He is especially interested in visual computing systems that can learn from video, reconstruct and generate dynamic worlds, and support action in physical environments.