Web Analytics Made Easy - Statcounter
Dr Ronald Clark
Imperial College Research Fellow
ronald.clark(at)imperial.ac.uk

Biography

Since October 2019 I hold an Imperial College Research Fellowship which is supporting my group to work on "Machine Learning for Light Field Capture and Rendering". Prior to this I was a postdoctoral research fellow at the Dyson Robotics Lab. I did my PhD at the University of Oxford Department of Computer Science where I held an EPSRC scholarship. Before coming to the UK, I did my BSc and MSc in electrical engineering at the University of the Witwatersrand in South Africa.

Research

Our world is inherently 3D, yet most of computer vision has (and is still) focussed on simple 2D tasks. I believe that any intelligent system that can robustly understand, interact and analyse the real world, will need to build and maintain native 3D representations that change and update over time. My research is currently focussed on building the necessary algorithmic frameworks to enable mobile devices to capture these 3D digital twins of the world. To achieve this, I am interested in three main aspects:

  • generative models for learning compact and interpretable representations
  • informative priors (physical, geometric, learned) for reliable inference
  • optimization techniques for inference and adaptation

Applications

My research has been applied in a number of application domains - from home robots, to mobile apps. Below are some examples of the capabilities that my reserach has enabled.

Realtime SLAM
Scene Understanding
Motion Analysis

Updates

  • Oct 2021 Co-organizing the 1st Challenge on Large Scale Point-cloud Analysis for Urban Scene Understanding at ICCV'21
  • Jun 2021 Serving as an Area Chair for BMVC’21
  • Nov 2020 Organizing a tutorial on 3D reconstruction and segmentation at 3DV’2020
  • Oct 2020 Invited talk at MILA/REAL Robot Learning Seminar series
  • Jul 2019 Invited Talk at the BMVA technical meeting on Geometry and Deep Learning.
  • Mar 2019 Our 2nd Workshop on Deep Learning for Visual SLAM will be held at ICCV’19!
  • Dec 2018 Co-organizing the CVPR’19 Workshop on Deep Learning for Visual Semantic Navigation

Awards and Fellowships

  • CVPR Best Paper Honourable Mention Award (2018)
  • Imperial College Research Fellowship (2019)
  • Outstanding Reviewer Award (CVPR'20, CVPR'21, ACCV'20)

Recent Talks