25th October 2017

John's McCormac work on SceneNet RGB-D was featured in the ICCV'17 daily magazine. John talks about his work to produce a large dataset for indoor segmentation tasks. More Info.


5th September 2017

Congratulations to Professor Andrew Davison for being selected to the Fellowship of the Royal Academy of Engineering. More Info.


24th July 2017

Two papers have been accepted from our group; one at IROS 2017 and one at ICCV 2017. Congratulations to Tristan and John. More Info.


14th July 2017

The 2nd Uk Robot Manipulation Workshop organised by Ed Johns, a Dyson Fellow at the Dyson Robotics Lab is featured today at Imperial's main website. A nice review of the workshop on robot manipulation that attracted 145 participants from UK academia and industry. More on this. 


10-11th July 2017

The 2nd UK Robot Manipulation Workshop will take place on Monday 10th and Tuesday 11th of July at Imperial College London. It is a UK-wide community-building event, bringing together researchers and engineers across both academia and industry. Topics will cover the full range of disciplines in robot manipulation, across both hardware and software, including mechanical design, sensor design, control, haptics, vision, and learning. The workshop is sponsored by Dyson Robotics Lab, Ocado Technology, Shadow Robot Company and IET. More info


3rd April 2017

New York Times journalist visited Professor Andrew Davison a couple of weeks ago. We are proud that our lab and work is mentioned in an article about Dyson pushished today. Click here to read the article


2nd February 2017

We have a Dyson sponsored fellowship available for an outstanding researcher. The deadline for submitting an application is 16th of February. Please follow the link for more information regarding this position.


17th January 2017

We have four papers accepted for ICRA 2017!

Robert Lukierski, Stefan Leutenegger and Andrew J. Davison. Room Layout Estimation from Rapid Omnidirectional Exploration, 2017, IEEE International Conference on Robotics and Automation (ICRA). (dyson funded)

John McCormac, Ankur Handa, Andrew J Davison, Stefan Leutenegger. SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks, 2017, IEEE International Conference on Robotics and Automation (ICRA). (dyson funded)

Sajad Saeedi, Luigi Nardi, Edward Johns, Bruno Bodin, Paul H J Kelly, Andrew J Davison. Application-oriented Design Space Exploration for SLAM Algorithms, 2017, IEEE International Conference on Robotics and Automation (ICRA). (non-dyson funded)

Lukas Platinsky, Andrew J. Davison, and Stefan Leutenegger. Monocular Visual Odometry: Sparse Joint Optimisation or Dense2017, IEEE International Conference on Robotics and Automation (ICRA). (non-dyson funded) 

18th December 2016


We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection, and also for geometric computer vision problems such as optical flow, depth estimation, camera pose estimation, and 3D reconstruction. Random sampling permits virtually unlimited scene configurations, and here we provide a set of 5M rendered RGB-D images from over 15K trajectories in synthetic layouts with random but physically simulated object poses. Each layout also has random lighting, camera trajectories, and textures. The scale of this dataset is well suited for pre-training data-driven computer vision techniques from scratch with RGB-D inputs, which previously has been limited by relatively small labelled datasets in NYUv2 and SUN RGB-D. It also provides a basis for investigating 3D scene labelling tasks by providing perfect camera poses and depth data as proxy for a SLAM system.

SceneNet RGB-D