JESSICA R. BARON
​
Graduate Student Research Assistant
Graduate Teacher-of-Record
​
Clemson University
School of Computing | Visual Computing Division
RESEARCH AND PUBLICATIONS
Professional Work during Graduate and Undergraduate Studies
THESIS RESEARCH
My thesis research focuses on physically based feathers in computer graphics. My master's thesis concerns procedurally generating the geometry of feathers based on information extracted from images of real feathers. My dissertation research focuses on measuring and developing a reflectance model for feathers.
Procedurally Generating Biologically Driven Bird and Non-Avian Dinosaur Feathers
This thesis focuses particularly on bird and other dinosaur feathers and their structure. More specifically, it addresses the problem of procedurally generating biologically driven geometry for modeling feathers in computer graphics. As opposed to previously published methods for generated feather geometry, data is derived from a myriad of real-world specimens of feathers and used in creating graphical models of feathers.
​
The PDF link opens up the thesis document.
COUNTENANCE LAB
​
The Countenance Lab is a research group at Clemson University in the Visual Computing division of the School of Computing. The lab focuses on 2D and 3D facial analysis, using techniques from computer vision, computer graphics, and machine learning. Ongoing projects include capture and study of human faces, material capture, and automated age progression.
Countenance Tool (Software)
The Countenance Tool is a user-friendly software interface for both 2D and 3D work on objects, particularly human faces. I have written this code and continue to add features as the Lab conducts new studies. The software is built in Python using PyQt5 bindings of the GUI library Qt5, through which GLSL-shader-based OpenGL 4.x is accessed for 3D rendering. The video captures the Tool performing part of the process used in re-topology project.
Re-topology of Human Faces
This project is focused on automating the re-topology of dense scans of human faces. Using a quadrangulated template mesh that follows the musculature of the human face, a series of Facial Action Coding System (FACS) scans of a subject are reduced to an edge layout following the template mesh using interactive 2D landmarking that triggers changes in a resulting 3D mesh.
​
This is an ongoing study. The merit of the idea is showcased as an ACM-SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D) 2018 poster.
​
Focusing on the llandmark-based approach, the re-topology study is discussed in an accepted paper at the International Conference on Computer Vision and Graphics (ICCVG) 2018 to be published in Springer's Lecture Notes in Computer Science journal.
Quad-Mesh AAMs
This project is on incorporating the use of a quadrangulated mesh rather than Delaunay Triangulation in Active Appearance Models (AAMs). The goal of this study is to show that a 2D quad-mesh that follows the musculature of the face can lead to image synthesis results that are better than those from a 2D triangular mesh created from landmarks.
FURTHER EXPERIENCE, RESEARCH, AND PUBLICATIONS
RenderMan Software-Development Internship at Pixar Animation Studios
I joined Pixar's RenderMan Group in Seattle, WA for 3 months where I implemented the Disney Principled BSDF for the RenderMan path-traced renderer, mentored by Per Christensen. I additionally researched hair shading models, assisted with the RenderMan XPU effort, and helped with the annual RenderMan Art & Science Fair co-located with ACM-SIGGRAPH. The associated image consists of garlic bulbs from the kitchen RenderMan Art Challenge with the Disney BSDF RenderMan material applied.
Software-Engineering Internship at Weta Digital
I completed a 3-month internship at the visual-effects studio Weta Digital, joining the "Fur and Feathers" team to help start a new, in-house procedural-feather tool. My work focused on developing a biologically accurate model for feathers, capturing parameters that change based on the type of feather and further alterations. I had done both research and development for this project, gathering and understanding information on the biology and physics of feathers along with developing a C++ library and external software plug-ins.
Real-Time Rocks: Shader-Based Labradorite
I helped create and present a real-time rendering assignment for a graduate-level course taking nature (specifically geology) as a source of inspiration. This was an accepted submission to the Groovy Graphics panel at SIGGRAPH 2018, and the abstract can be found here in the ACM Digital Library:
Computer Graphics Research in Germany
Technical University of Cologne (TH Köln), Summer 2017
​
I procedurally modeled feathers using C++ and OpenGL at the Applied Science University of Cologne (TH Köln), institute of media- and Imaging Technology, through Germany's Universities of Applied Science (UAS7) through which I also had the opportunity to participate as a cultural ambassador.
Procedural Dungeon Generation
Clemson University, 2017
​
During my time at Clemson University, I have written an ACM peer-reviewed paper, "Procedural Dungeon Generation Analysis and Adaptation" for ACM Southeast 2017 Paper (on ACM Digital Library). See more details at the Dungeon Generator Project under the Development tab.
UNCW IS3 (Face Aging Group)
UNC-Wilmington, 2015-2016
As an undergraduate, computer-science student, I worked with the UNCW Institute for Interdisciplinary Identity Sciences (I3S), also called the Face Aging Group, Here is where I began research on 2D and 3D facial analysis, and I have assisted in other projects such as printed circuit board (PCB) component identification and identifying the effects of smoking on health through faces.
I am an author on the peer-reviewed paper "Collaboratively Designing and Building an Extensible Software Toolset for 2D and 3D Facial Modeling and Analysis" at ACM Mid-Southeast 2016. I also presented on this topic at the UNCW CSURF Research Showcase. At the same event, I presented a second poster on "From Physical Collection to 3D Model Construction: Building the METAL PCB Dataset" on my contributions to the circuit board study. The image to the left is a depth-buffer render of a 3D mesh of one of the dataset's PCBs. Check out the poster here.