Mengkun She | 佘梦坤

Hi! I'm a computer vision research engineer at Dandy, the digital dental lab working on accurate geometry and appearance capture for human teeth using image-based 3D modeling and inverse rendering. Before joining Dandy, I did my PhD at Institute of Computer Science, Christian-Albrechts-Universität zu Kiel in Germany. Previously, I was working in the Marine Data Science group advised by Prof. Dr. Kevin Köser.

Before moving to Kiel University, I was a computer vision research assistant in the Oceanic Machine Vision group at GEOMAR Helmholtz-Zentrum für Ozeanforschung Kiel.

Dandy CAU Kiel GEOMAR

Research

At MDS group, we focus on Artificial Intelligence and Perception for the Marine Sciences and Environments, in particular at the interface of Computer Vision, Computer Graphics, Robotics and Machine Learning. We therefore need to deal with challenging but very interesting real-world images acquired by deep-sea robots. Highlights are the major works.

Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects
David Nakath, Xiangyu Weng, Mengkun She, Kevin Köser
International Conference on 3D Vision (3DV), 2024
Preprint / Poster / Supplementary Material / Data

How to establish 3D models of partially translucent organisms? We adapt Differentiable Raytracing to real data to capture Tomography-like internal structure, establish relightable models, immerse models in other media, and exhibit high novel-view stability.

Services

Teaching Assistant: Probabilistic Robotics, Winter 2023, CAU (now renamed to Mobile Robotics)