activity
20202025
most citedAdvanced Underwater Image Restoration in Complex Illumination Conditions

35 citations · 90 across the 9 of their papers we have counts for

collaborators

11 papers

cs.CV2025

Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes

Mengkun She, Felix Seegräber, David Nakath +2

We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light…

cs.CV2024

A Calibration Tool for Refractive Underwater Vision

Felix Seegräber, Mengkun She, Felix Woelk +1

Many underwater applications rely on vision sensors and require proper camera calibration, i.e. knowing the incoming light ray for each pixel in the image. While for the ideal pinh…

cs.CV2024★ 9 cited

Refractive COLMAP: Refractive Structure-from-Motion Revisited

Mengkun She, Felix Seegräber, David Nakath +1

In this paper, we present a complete refractive Structure-from-Motion (RSfM) framework for underwater 3D reconstruction using refractive camera setups (for both, flat- and dome-por…

cs.CV2023

Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects

David Nakath, Xiangyu Weng, Mengkun She +1

When created faithfully from real-world data, Digital 3D representations of objects can be useful for human or computer-assisted analysis. Such models can also serve for generating…

cs.CV2023★ 35 cited

Advanced Underwater Image Restoration in Complex Illumination Conditions

Yifan Song, Mengkun She, Kevin Köser

Underwater image restoration has been a challenging problem for decades since the advent of underwater photography. Most solutions focus on shallow water scenarios, where the scene…

cs.CV2023★ 6 cited

Semihierarchical Reconstruction and Weak-area Revisiting for Robotic Visual Seafloor Mapping

Mengkun She, Yifan Song, David Nakath +1

Despite impressive results achieved by many on-land visual mapping algorithms in the recent decades, transferring these methods from land to the deep sea remains a challenge due to…

cs.RO2023★ 11 cited

Investigation of the Challenges of Underwater-Visual-Monocular-SLAM

Michele Grimaldi, David Nakath, Mengkun She +1

In this paper, we present a comprehensive investigation of the challenges of Monocular Visual Simultaneous Localization and Mapping (vSLAM) methods for underwater robots. While sig…

cs.CV2021★ 21 cited

Marine Bubble Flow Quantification Using Wide-Baseline Stereo Photogrammetry

Mengkun She, Tim Weiß, Yifan Song +3

Reliable quantification of natural and anthropogenic gas release (e.g.\ CO, methane) from the seafloor into the water column, and potentially to the atmosphere, is a challengin…

cs.CV2021

Refractive Geometry for Underwater Domes

Mengkun She, David Nakath, Yifan Song +1

Underwater cameras are typically placed behind glass windows to protect them from the water. Spherical glass, a dome port, is well suited for high water pressures at great depth, a…

cs.CV2020

Light Pose Calibration for Camera-light Vision Systems

Yifan Song, Furkan Elibol, Mengkun She +2

Illuminating a scene with artificial light is a prerequisite for seeing in dark environments. However, nonuniform and dynamic illumination can deteriorate or even break computer vi…

cs.CV2020★ 8 cited

Deep Sea Robotic Imaging Simulator

Yifan Song, David Nakath, Mengkun She +2

Nowadays underwater vision systems are being widely applied in ocean research. However, the largest portion of the ocean - the deep sea - still remains mostly unexplored. Only rela…