Mengkun She | 佘梦坤

Hi! I'm a Ph.D. student at the Institute of Computer Science, Christian-Albrechts-Universität zu Kiel in Germany. Here, I'm 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

Email  /  CV  /  Scholar  /  Github

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.

Underwater cameras suffer from geometric distortion induced by refraction of light rays at the water-glass-air interfaces. There has been works going on to analyze and calibrate such systems. However, we ask the question: what are you going to do with the calibrated refractive cameras? Can you use it in structure-from-motion? We therefore integrate the refractive geomtry within the COLMAP framework and release it as open-source.

A semi-hierarchical approach which combines the good parts of incremental and global structure-from-motion for large-scale AUV-based monocular camera seafloor reconstruction. Weak-area revisiting helps to mitigate inconsistencies in the reconstructed camera poses and map.

How to establish 3D models of partially translucent organisms? We adapt Differentiable Raytracing to real data to: 1. capture Tomography-like internal structure; 2. establish relightable models; 3. immerse models in other media; 4. exhibit high novel-view stability

A 3D look-up-table to represent the complex illumination field for underwater image restoration tasks.

The BubbleBox project aims to develop a high-speed stereo camera system that can be deployed on the seafloor of the deep ocean to measure and quantify the amount of gas released from the seafloor into the water column. Checkout the livestream of the BubbleBox deployment!

We made a survey on different state-of-the-art underwater image restoration methods for deep-sea optical imaging systems.

As the name suggests: a digital twin for underwater photogrammetry research. We particularly target at refractive geometric verification.

We look more into the refractive geometry properties of underwater dome-port cameras.

We discover that the camera model of a focus stacked image is essentially an affine model. We then propose a macro-lens calibration approach based on this insight for 3D reconstruction of very tiny objects using such cameras. This technology is used in the TechOceanS project.

3D reconstruction using a camera with an active light source creates an uneven and color-distorted texture. We use physically-based differentiable ray-tracing to firstly estimate the light source in a calibration scenario, and then optimize a medium- and light- free texture in the subsequent SfM step.

A imaging simulator for deep-sea robots equipped with active light source.

Experimental study on illumination invariant features!

In this work, we develop an effective method to align a camera with an underwater spherical port (dome-port) for underwater camera systems. This technique is essential for the accurate calibration of our underwater cameras.

Services

Yep I know this is another Jon Barron website.