About me

I’m a Research Scientist working at Facebook Reality Labs, Pittsburgh. I’m working on creating techniques to render and animate photorealistic virtual humans in real time. To do this, I’m combining ideas from computer graphics, computer vision, and machine learning. I got my Ph.D. in 2016 from Drexel University, advised by Ko Nishino, and I got my Bachelor’s degree in 2009 from The College of New Jersey.

Recent Projects

Neural Volumes

Neural Volumes

Neural Volumes is a method for representing dynamic objects, supervised directly from 2D images from a multi-view capture stage.

Read more

Deep Appearance Models

Deep Appearance Models

Deep Appearance Models is a method for creating high-quality face models and driving them from a cameras mounted on a VR headset.

Read more

Full Publication List

Neural Volumes: Learning Dynamic Renderable Volumes from Images
Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, Yaser Sheikh
ACM Transactions on Graphics (SIGGRAPH 2019) 38, 4, Article 65
[ arXiv ] [ supplemental video ] [ code & data ] [ bibtex ]

VR Facial Animation via Multiview Image Translation
Shih-En Wei, Jason Saragih, Tomas Simon, Adam W. Harley, Stephen Lombardi, Michal Perdoch, Alexander Hypes, Dawei Wang, Hernan Badino, Yaser Sheikh
ACM Transactions on Graphics (SIGGRAPH 2019) 38, 4, Article 67
[ PDF ] [ supplemental video ]

Deep Appearance Models for Face Rendering
Stephen Lombardi, Jason Saragih, Tomas Simon, Yaser Sheikh
ACM Transactions on Graphics (SIGGRAPH 2018) 37, 4, Article 68
[ arXiv ] [ supplemental video ] [ talk video ] [ bibtex ]

Radiometric Scene Decomposition: Estimating Complex Reflectance and Natural Illumination from Images
Stephen Lombardi
Ph.D. Thesis

Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images
Stephen Lombardi and Ko Nishino
4th International Conference on 3D Vision, October 2016
[ arXiv ]

Reflectance and Illumination Recovery in the Wild
Stephen Lombardi and Ko Nishino
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 1, May 2015

Two-Point Gait: Decoupling Gait from Body Shape
Stephen Lombardi, Ko Nishino, Yasushi Makihara, Yasushi Yagi
14th International Conference on Computer Vision, December 2013

Reflectance and Natural Illumination from a Single Image
Stephen Lombardi and Ko Nishino
12th European Conference on Computer Vision, October 2012
[ talk video ]

Bayesian Defogging
Ko Nishino, Louis Kratz, and Stephen Lombardi
International Journal of Computer Vision, vol. 98, no. 3, pg 263-278, July 2012

Single Image Multimaterial Estimation
Stephen Lombardi and Ko Nishino
25th IEEE Conference on Computer Vision and Pattern Recognition, June 2012

Directional Statistics-based Reflectance Model for
Isotropic Bidirectional Reflectance Distribution Functions

Ko Nishino and Stephen Lombardi
Journal of the Optical Society of America A, vol. 28, no. 1, pg 8-18, January 2011