Computer Vision

The Computer Vision Group (CVG) at the Toshiba Cambridge Laboratory is developing advanced research using digital images to enable machines to interpret and reason about the world. CVG’s research aims at creating new technologies for artificial intelligent systems to have a positiveimpact on society and industry at large scale. To achieve this, groundbreaking research is carried out from an academic level to a maturefunctioning stage. Artificial intelligence is pushed beyond its limits to overcome challenges and make visual understanding effective.

Research areas

The CVG is conducting cutting edge research on a number of fields leading fundamental research to pioneer applications.


Driven by academic research results, the CVG contribution to the state-of-the-art methods in Computer Vision passes through shared resources to ensure reproducibility of results.

Selected Publications

Modelling Partially Observable Systems using Graph-based Memory and Topological Priors

S. Morad, S. Liwicki, R. Kortvelesy, R. Mecca, A. Prorok
Learning for Dynamics and Control Conference

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

R. Mecca, F. Logothetis, I. Budvytis and R. Cipolla
British Machine Vision Conference

PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks

F. Logothetis, I. Budvytis, R. Mecca, R. Cipolla
International Conference on Computer Vision

Lifted Semantic Graph Embedding for Omnidirectional Place Recognition

C. Zhang, I. Budvytis, S. Liwicki and R. Cipolla
International Conference on 3D Vision

View more

Latest Publications

S Morad, R Kortvelesy, M Bettini, S Liwicki, A Prorok

P Pathre, A Sahu, A Rao, A Prabhu, M Nigam, T Karandikar, H Pandya, M Krishna

P Somaiya, H Pandya, R Polvara, M Hanheide, G Cielniak

View more