Research Highlights: By Topic

My research is broadly inspired by real-time and interactive applications and spans the fields of computer vision and computer graphics. I have also written many real-time vision and graphics demos and constructed multiple novel data capture systems used to create widely distributed datasets.
Complete chronological list of publications is here.
Generic placeholder image

Computer Vision

View details »

Generic placeholder image

Computer Graphics

View details »

Generic placeholder image

Human Interaction

View details »


Computer Vision: Tracking

The Lucas-Kanade 20 Years On series of papers defined a new framework for gradient descent image alignment. Our inverse-compositional algorithm introduced a new and computationally efficient algorithm for tracking.

The Matlab source code for Lucas-Kanade 20 years on: A unifying framework is available here.

Generic placeholder image
Equivalence and efficiency of image alignment algorithms Simon Baker and Iain Matthews IEEEComputer Society Conference on Computer Vision and Pattern Recognition, pages 1090–1097, 2001 PaperDOI
Generic placeholder image
Lucas-Kanade 20 years on: A unifying framework Simon Baker and Iain Matthews International Journal of Computer Vision, 56(3):221–255, February 2004 PaperDOIMatlab source code
Generic placeholder image
The template update problem Iain Matthews, Takahiro Ishikawa, and Simon Baker IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6):810–815, June 2004 PaperDOI

Computer Vision: Face Tracking

Extending the inverse-compositional image alignment approach to allow complex warps and appearance change enabled real-time Active Appearance Models (back in time when real-time face tracking was hard).

Generic placeholder image
Active appearance models revisited Iain Matthews and Simon Baker International Journal of Computer Vision, 60(2):135–164, November 2004 PaperDOI
Generic placeholder image
Generic vs. person specific active appearance models Ralph Gross, Iain Matthews, and Simon Baker Image and Vision Computing, 23(11):1080–1093, November 2005 PaperDOI
Generic placeholder image
2D vs. 3D Deformable face models: Representational power, construction and real-time fitting Iain Matthews, Jing Xiao, and Simon Baker International Journal of Computer Vision, 75(1):93–113, October 2007 PaperDOI

Computer Vision: Face Modeling 

Data-driven approaches to facial modeling enable compelling computer graphics that support intuitive interaction.

Generic placeholder image
Interactive region-based linear 3D face models J. Rafael Tena, Fernando De la Torre, and Iain Matthews ACM Transactions on Graphics (Proc. ACM SIGGRAPH), August 2011 PaperDOI
Generic placeholder image
Photogeometric sceneflow for high-detail dynamic 3D reconstruction Paulo F. U. Gotardo, Tomas Simon, Yaser Sheikh, and Iain Matthews Proc. International Conference on Computer Vision, December 2015 PaperDOI

Computer Graphics: Face Animation

Data-driven and machine learning approaches to facial animation allow us to move away from intuition defined units and controls.

Generic placeholder image
Dynamic units of visual speech Sarah L. Taylor, Moshe Mahler, Barry-John Theobald, and Iain Matthews Eurographics / ACM SIGGRAPH Symposium on Computer Animation, July 2012 PaperDOI
Generic placeholder image
Predicting head pose from speech with a conditional variational autoencoder David Greenwood, Stephen Laycock, and Iain Matthews Interspeech, pages 3991–3995, August 2017 PaperDOI

Computer Graphics: Light

Optimization and machine learning approaches to estimating light for content creation and relighting.

Generic placeholder image
Lighting estimation in outdoor image collections Jean-François Lalonde and Iain Matthews Proc. International Conference on 3D Vision, December 2014 PaperDOI

Human Interaction: Measuring Groups 

Generic placeholder image
Factorized variational autoencoders for modeling audience reactions to movies Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, and Greg Mori IEEE Computer Society Conference on Computer Vision and Pattern Recognition, July 2017 PaperDOI
Generic placeholder image
Panoptic studio: A massively multiview system for social interaction capture Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, and Yaser Sheikh IEEE Transactions on Pattern Analysis and Machine Intelligence, August 2017 PaperDOI — Journal version of ICCV 2015

Human Interaction: Sports Analytics 

Generic placeholder image
Large-scale analysis of soccer matches using spatiotemporal tracking data Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Sridha Sridharan, and Iain Matthews Proc. IEEE International Conference on Data Mining, December 2014 PaperDOI
Generic placeholder image
Discovering team structures in soccer from spatiotemporal data Alina Bialkowski, Patrick Lucey, Peter Carr, Iain Matthews, Clinton Fookes, and Sridha Sridharan IEEE Trans. on Knowledge and Data Engineering, 28(10):2596–2605, October 2016 PaperDOI
© Iain Matthews, 2018