Computer Vision

CRL’s Computer Vision Group (CVG) conducts cutting-edge research in 3D computer vision and machine learning with the aim to improve the ability of software to understand and interpret visual data. In our work we support Toshiba’s overall mission to create modern technology with a positive impact on society. Our main focus is on fundamental and academically oriented research, and consequently we also have ongoing collaborations with top UK universities.

More about CVG ►



Research

Online Structure from Motion

The problem of online structure from motion is also known as simultaneous localisation and mapping. It involves a system that estimates a sensor’s pose and the structure of the environment in real-time. We develop methods for visual odometry, loop closure detection and pose graph optimization.

Scale Exploiting Minimal Solvers for Relative Pose with Calibrated Cameras, S. Liwicki et al., BMVC (2017)

Online Variational Bayesian Motion Averaging, G. Bourmaud, ECCV (2016)

The Likelihood-Ratio Test and Efficient Robust Estimation, A. Cohen et al., ICCV (2015)

Learn more ►
Online Structure from Motion

Visual Text-to-Speech

In collaboration with CRL’s Speech Technology Group we produced a complete system for expressive visual text-to-speech. Our system is able to producing expressive verbal and visual output in the form of a 'talking head', given an input text and a set of continuous expression weights.

Expressive Visual Text-to-Speech as an Assistive Technology for Individuals with Autism Spectrum Conditions, S. A. Cassidy et al., CVIU (2016) / free

Photo-Realistic Expressive Text to Talking Head Synthesis, V. Wan et al., Interspeech (2013) / free

Learn more ►
Visual Text-to-Speech

Optimization Methods

Energy-minimization methods are ubiquitous in computer vision and related fields. In our work we design efficient low-level optimization strategies at pixel level, and robust optimization methods for 3D vision problems with high complexity.

pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment, J. H. Hong et al., CVPR (2018) / free

Maximum Consensus Parameter Estimation by Reweighted ℓ1 Methods, P. Purkait et al., EMMCVPR (2017)

Generalized Fusion Moves for Continuous Label Optimization, C. Zach, ACCV (2016)

Learn more ►
Optimization Methods

Publications

A Differential Volumetric Approach to Multi-View Photometric Stereo
F. Logothetis, R. Mecca, R. Cipolla
ICCV, in print arXiv

Orientation-aware Semantic Segmentation on Icosahedron Spheres
C. Zhang, S. Liwicki, W. Smith, R. Cipolla
ICCV, in print arXiv

Fast-SCNN: Fast Semantic Segmentation Network
R. P. K. Poudel, S. Liwicki, R. Cipolla
BMVC, in print arXiv

Learning Monocular Visual Odometry with Dense 3D Mapping from Dense 3D Flow
C. Zhao, L. Sun, P. Purkait, T. Ducket and R. Stolkin
IROS, October 2018 arXiv

Descending, Lifting or Smoothing: Secrets of Robust Cost Optimization
C. Zach and G. Bourmaud
ECCV, September 2018 / free

More CVG Publications ►