Stephen DiVerdi

Senior Research Scientist

Creative Intelligence Lab, San Francisco

Stephen joined the Creative Technologies Lab in San Francisco under David Salesin in June 2015, but has worked for Adobe Research off and on since 2000, over the course of three internships and 5 years in the San Jose office.  His background is in augmented reality and digital multimedia, and his research interests include natural media painting, 3D graphics, realtime rendering, machine learning, and virtual reality.  More generally, his goal is to enable artists by developing new creative tools. During his work at Adobe he has shipped a number of natural media features in Photoshop, Illustrator, and our iOS apps.

Stephen received his B.S. in computer science from Harvey Mudd College in 2002 and his Ph.D. in augmented reality in 2007 from University of California in Santa Barbara, where he was advised by Tobias Höllerer in the Four Eyes Lab.  He worked at Adobe Research under Gavin Miller from 2007 to 2012, after which he joined Google.  During 2013, he was on the Google+ Photos team developing machine learning algorithms for the autoenhance feature with Aravind Krishnaswamy.  In 2014 he joined Marc Levoy’s computational photography team in Google [x] where I worked on calibration of camera arrays.

My Publications

Pigmento: Pigment-Based Image Analysis and Editing

Tan, J., DiVerdi, S., Lu, J., Gingold, Y. (Aug. 1, 2018)
IEEE Transactions on Visualization and Computer Graphics (TVCG)

Learning A Stroke-Based Representation for Fonts

Balashova, E., Bermano, A., Kim, V., DiVerdi, S., Hertzmann, A., Funkhouser, T. (May. 31, 2018)
Computer Graphics Forum

Playful Palette: An Interactive Parametric Color Mixer for Artists

Shugrina, M., Lu, J., DiVerdi, S. (Aug. 1, 2017)
ACM Transactions on Graphics (Proc. of SIGGRAPH 2017)

VoCo: Text-based Insertion and Replacement in Audio Narration

Jin, Z., Mysore, G., DiVerdi, S., Lu, J., Finkelstein, A. (Aug. 1, 2017)
ACM Transactions on Graphics (Proc. of SIGGRAPH 2017)

VoCo: text-based insertion and replacement in audio narration

Jin, Z., Mysore, G., DiVerdi, S., Lu, J., Finkelstein, A. (Jul. 31, 2017)
ACM Transactions on Graphics (TOG) 36, no. 4 (2017): 96.

CUTE: a Concatenative Method for Voice Conversion Using Exemplar-based Unit Selection

Jin, Z., Finkelstein, A., DiVerdi, S., Lu, J., Mysore, G. (Mar. 1, 2016)
The 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

RealPigment: Paint Compositing by Example

Lu, J., DiVerdi, S., Chen, W., Barnes, C., Finkelstein, A. (Jun. 1, 2014)
Best paper award. NPAR 2014 – Proceedings of the ACM/Eurographics Symposium on Non-Photorealistic Animation and Rendering

Learning Part-based Templates from Large Collections of 3D Shapes

Kim, V., Li, W., Mitra, N., Chaudhuri, S., DiVerdi, S., Funkhouser, T. (Aug. 1, 2013)
SIGGRAPH

RealBrush: Painting with Examples of Physical Media

Lu, J., Barnes, C., DiVerdi, S., Finkelstein, A. (Jul. 1, 2013)
ACM Transactions on Graphics (Proc. of SIGGRAPH 2014)

A Procedural Watercolor Engine

DiVerdi, S., Krishnaswamy, A., Měch, R., Ito, D. (May. 1, 2013)
IEEE Transactions on Visualization and Computer Graphics.

Exploring Collections of 3D Models using Fuzzy Correspondences

Kim, V., Li, W., Mitra, N., DiVerdi, S., Funkhouser, T. (Aug. 31, 2012)
SIGGRAPH

HelpingHand: Example-based Stroke Stylization

Lu, J., Yu, F., Finkelstein, A., DiVerdi, S. (Jul. 1, 2012)
ACM Transactions on Graphics (Proc. of SIGGRAPH 2012), 31(4), July 2012

A lightweight, procedural, vector watercolor painting engine

DiVerdi, S., Krishnaswamy, A., Měch, R., Ito, D. (Apr. 3, 2012)
Best Paper Award In Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D '12), 2012.

Bristle Tip and Mixer Brush

Hadap, S., DiVerdi, S., Krishnaswamy, A. (Jan. 31, 2010)
Poster, NPAR 2010

Industrial-Strength Painting with a Virtual Bristle Brush

DiVerdi, S., Krishnaswamy, A., Hadap, S. (Jan. 31, 2010)
In Proc. of the Symposium on Virtual Reality Software and Technology , 119-126

Industrial-Strength Painting with a Virtual Bristle Brush

DiVerdi, S., Krishnaswamy, A., Hadap, S. (Jan. 30, 2010)
VRST 2010

A Sketch-Based Interface for Photo Pop-up

Ventura, J., DiVerdi, S., Höllerer, T. (Jan. 31, 2009)
In Proc. of Sketch-Based Interfaces and Modeling , 21-28

All Around the Map: Online Spherical Panorama Construction

DiVerdi, S., Wither, J., Höllerer, T. (Jan. 31, 2009)
In Computers and Graphics , 22 (1): 73-84

Depth-Fused 3D Imagery on an Immaterial Display

Lee, C., DiVerdi, S., Höllerer, T. (Jan. 31, 2009)
In IEEE Transactions on Visualization and Computer Graphics , 15(1): 20-23

Heads Up and Camera Down: A Vision-based Tracking Modality for Mixed Reality

DiVerdi, S., Höllerer, T. (Oct. 15, 2008)
IEEE Transactions on Visualization and Computer Graphics , 14(3): 500-512

Envisor: Online Environment Map Construction for Mixed Reality

DiVerdi, S., Wither, J., Höllerer, T. (Apr. 21, 2008)
In Proc. IEEE Virtual Reality , 19-26

GroundCam: A Tracking Modality for Mobile Mixed Reality

DiVerdi, S., Höllerer, T. (Feb. 20, 2007)
In Proc. IEEE Virtual Reality , 75–82

Three-dimensional Television: Capture, Transmission and Display, eds. Ozaktas, H. and Onural, L.. Springer, ch

DiVerdi, S., Olwal, A., Rakkolainen, I., Höllerer, T. (Feb. 6, 2007)
An Immaterial Pseudo-3D Display with 3D Interaction , 505–528