cv Katherine A. Skinner


I am a PhD Candidate in Robotics at the University of Michigan working in the Deep Robot Optical Perception (DROP) Lab. My research interests include perception for marine robotics, light field imaging, and unsupervised learning. I hold an M.S. in Robotics from University of Michigan and a B.S.E. in Mechanical and Aerospace Engineering with a Certificate in Applications of Computing from Princeton University.

[CV][Google Scholar]


May 21, 2018

Today I started a summer internship with NVIDIA!

April 13, 2018

I was honored to be a part of the groundbreaking ceremony for the UM's Ford Robotics Building. I am so excited for the students of UM Robotics to finally have a place to call home. Read more [here].

February 7, 2018

I just returned from two weeks of field work at Hawaii Institute of Marine Biology - research with a view!

December 8, 2017

Our first tank test with DROP Lab's BlueROV2 went swimmingly. It was great working at the new underwater test facility at CMU's Field Robotics Center.

September 22, 2017

I spent the last week conducting field work at the Bermuda Institute of Ocean Sciences (BIOS). Our lab is working with a team of scientists from WHOI and the University of Georgia to create 3D reconstructions of coral reef sites off the coast of Bermuda.

September 12, 2017

Check out this awesome video on research and field work with DROP Lab!

August 29, 2017

Welcome to the new graduate students of the Robotics Institute at the University of Michigan! I had fun at the 3rd Annual Robotics Student Welcome Picnic organized by the Robotics Graduate Student Council.

July 26, 2017

I had a great time in Honolulu, HI where I presented recent work on underwater image dehazing for light field images at the CVPR 2017 Light Field Workshop.

June 3, 2017

ICRA 2017 was great! I presented work on integrating color correction into bundle adjustment for 3D reconstruction of underwater scenes.

April 12, 2017

I am excited to be featured in UM Central Student Government's "200 for 200" series in celebration of the 200th Anniversary of the University of Michigan!


Unsupervised Learning for Underwater Imagery

Deep learning has demonstrated great success in modeling complex nonlinear systems but requires a large amount of training data, which is difficult to compile in deep sea environments. Using WaterGAN, we generate a large training dataset of paired imagery, both raw underwater and true color in-air, as well as depth data. This data serves as input to a novel end-to-end network for color correction of monocular underwater images. Due to the depth-dependent water column effects inherent to underwater environments, we show that our end-to-end network implicitly learns a coarse depth estimate of the underwater scene from monocular underwater images.

Light Field Imaging in Underwater Environments

Light field cameras have a microlens array between the camera's main lens and image sensor, enabling recovery of a depth map and high resolution image from a single optical sensor. I am interested in using light field cameras for underwater perception.

Underwater Bundle Adjustment

Our work developing underwater bundle adjustment integrates color correction into the structure recovery procedure for multi-view stereo reconstruction in underwater environments.

Robotic Survey of Sunken Pirate City

Our team conducted a robotic survey of the submerged city of Port Royal, Jamaica to create a 3D reconstruction of the marine archaeological site. [Read more]


"WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images." (Jie Li*, Katherine A. Skinner*, Ryan Eustice, and Matthew Johnson-Roberson), In IEEE Robotics and Automation - Letters, 2017. *The authors contributed equally to this work. [BibTeX, PDF]

”Multi-view 3D Reconstruction in Underwater Environments: Evaluation and Benchmark.” (Eduardo Iscar, Katherine A. Skinner, and Matthew Johnson-Roberson), In MTS/IEEE OCEANS, 2017.[BibTeX]

”Underwater Image Dehazing with a Light Field Camera.” (Katherine A. Skinner and Matthew Johnson-Roberson), In IEEE Conference on Computer Vision and Pattern Recognition – Workshops, 2017 (Oral Presentation).[BibTeX]

"Automatic Color Correction for 3D Reconstruction of Underwater Scenes ." (Katherine A. Skinner, Eduardo Iscar, and Matthew Johnson-Roberson), In IEEE International Conference on Robotics and Automation, 2017. [BibTeX]

"Towards Real-time Underwater 3D Reconstruction with Plenoptic Cameras." (Katherine A. Skinner and Matthew Johnson-Roberson), In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016. [BibTeX][PDF]

"Detection and Segmentation of Underwater Archaeological Sites Surveyed with Stereo-Vision Platforms." (Katherine A. Skinner and Matthew Johnson-Roberson), In MTS/IEEE OCEANS, 2015. [BibTeX][PDF]

"Bathymetric factor graph SLAM with sparse point cloud alignment." (Vittorio Bichucher, Jeffrey M. Walls, Paul Ozog, Katherine A. Skinner, and Ryan M. Eustice), In MTS/IEEE OCEANS, 2015.[BibTeX, PDF]


NAVARCH 599: Underwater Robotics -- Winter 2018, Guest Lecturer

This course is an introduction to underwater robotics offered to upper class undergraduates and graduate students.

EECS 442: Computer Vision -- Fall 2016, Graduate Student Instructor

This course is an introduction to 2D and 3D computer vision offered to upper class undergraduates and graduate students. Topics include camera models, multi-view geometry, stereo reconstruction, low-level image processing methods, segmentation, clustering, and high-level vision techniques such as object recognition.

ENG 100: Introduction to Engineering -- Fall 2016, Guest Lecturer

This course is an introduction to underwater vehicle design for freshmen undergraduates. [Lecture Slides]



Our lab coordinated with Wayne State University's Gaining Options - Girls Investigate Real Life (GO-GIRL) program to design a summer workshop for high school girls as an introduction to engineering. The workshop involved building a SeaPerch remotely operated vehicle (ROV) and testing it in a lab setting and in a local pond to gather data. [Tutorial]

Discover Engineering

The Robotics Graduate Student Council organized a workshop for UM College of Engineering's Discover Engineering program. The program is geared towards 8th-10th graders who are children of UM alumni. Our workshop featured a fun robot bowling challenge! [Workshop Slides]

Robotics Day

UM hosts Robotics Day each year, bringing together industry, academia, and government agencies to highlight robotics advances across Michigan. This year the Robotics Graduate Student Council hosted a table where young roboticists could design, build, and test their very own drawing robots. [Workshop Handout]

More Involvement

Robotics Graduate Student Council - Outreach Chair, Co-founder (Past: President, Treasurer)
NSF IS-GEO Research Coordination Network - Early Career Committee
Undergraduate Research Opportunity Program - Mentor
Mentor2Youth Program - Instructor [Tutorial]
GradSWE Elementary School Science Program - Instructor
Robotics Day Planning Committee - Student Representative
A World in Motion - Instructor