Toshiba Cambridge Research Laboratory
Cambridge Research Laboratory > Computer Vision

Computer Vision

CRL's Computer Vision Group (CVG) is working on new methods for 3D Computer Vision, Machine Learning, and Optimization applied to visual data. CVG was founded in 2006 and is currently managed by Dr Stephan Liwicki with scientific guidance by Dr Christopher Zach and strategic advice by Professor Roberto Cipolla FREng. Our mission is to conduct fundamental computer vision research for future technology and products, and we actively collaborate with the University of Cambridge and the Toshiba Corporate R&D Center in Japan.

Image of cottage with one side rendered and the other shown as a wire frame.

The current focus of the group is 3D reconstruction and machine learning, and members of CVG work on multi-view geometry, SLAM, dense 3D modelling, and deep learning in particular. Since our target applications are in the area of autonomous systems and social infrastructure, we are especially interested in real-time methods for computer vision.

Toshiba Research Europe Limited (TREL) is part of Toshiba’s global R&D activity. The Cambridge Research Laboratory of TREL conducts research on computer vision, as well as quantum information technology, and speech recognition and dialogue.


(in alphabetical order)

Picture of Ujwal Bonde
Ujwal Bonde
Picture of Stephan Liwicki
Stephan Liwicki
Picture of Rudra Poudel
Rudra Poudel
Picture of Pulak Purkait
Pulak Purkait
Picture of Christopher Zach
Christopher Zach

Latest Publications

2017 2016 2015
Iterated Lifting for Robust Cost Optimization
C. Zach and G. Bourmaud
BMVC, September 2017
Scale Exploiting Minimal Solvers for Relative Pose with Calibrated Cameras
S. Liwicki and C. Zach
BMVC, September 2017
Revisiting the Variable Projection Method for Separable Nonlinear Least Squares Problems
J. Hong, C. Zach and A. Fitzgibbon
CVPR, July 2017
2017 2016 2015
Generalized Fusion Moves for Continuous Label Optimization [best paper]
C. Zach
ACCV, November 2016
Coarse-to-Fine Planar Regularization for Dense Monocular Estimation
S. Liwicki, C. Zach, O. Miksik and P. Torr
ECCV, October 2016
Online Variational Bayesian Motion Averaging
G. Bourmaud
ECCV, October 2016
Projective Bundle Adjustment from Arbitrary Initialization using the Variable Projection Method
J.H. Hong, C. Zach, A. Fitzgibbon and R. Cipolla
ECCV, October 2016
Dense Semantic 3D Reconstruction
C. Haene, C. Zach, A. Cohen and M. Pollefeys
IEEE T. PAMI, September 2016
Expressive Visual Text-to-Speech as an Assistive Technology for Individuals with Autism Spectrum Conditions
S. Cassidy, B. Stenger, L. Van Dongen, K. Yanagisawa, R. Anderson, V. Wan, S. BaronCohen and R. Cipolla
CVIU, 2016
How Many Bits Do I Need for Solving Pairwise Tests-based Binary Descriptors Matching Problems
P. Alcantarilla and B. Stenger
ICRA, 2016
Street-View Change Detection with Deconvolutional Networks
P. Alcantarilla, S. Stent, G. Ros, R. Arroyo and R. Gherardi
RSS, 2016
2017 2016 2015
The Likelihood-Ratio Test and Efficient Robust Estimation
A. Cohen and C. Zach
ICCV, December 2015
Detecting Change for Multi-View, Long Term Surface Inspection
S. Stent, R. Gherardi, B. Stenger and R. Cipolla
BMVC, September 2015
A Message-Passing Approach for Fast Object and Pose Recognition from Range Images
C. Zach, A. Penate Sancehez and M.T. Pham
CVPR, June 2015
Hierarchical Structure-and-Motion Recovery from Uncalibrated Images
R. Toldo, R. Gherardi, M. Farenzena and A. Fusiello
CVIU, June 2015
Towards Life-Long Visual Localization Using an Efficient Matching of Binary Sequences from Images
R. Arroyo, P. F. Alcantarilla, L. M. Bergasa and E. Romera
ICRA, May 2015
To Top