Ronald Clark

My aim is to make machines that can perceive, analyse and understand the world the way we do.

Biography

I am a research fellow at Imperial College London, where I work on machine learning for 3D vision. I was recently fortunate enough to receive an Imperial College Research Fellowship. I did my PhD at the University of Oxford Department of Computer Science where I was funded by 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 overview

My research centers around 3D machine perception which is needed to enable mobile devices to model, explore and understand their surroundings. I am particularly interested in ways in which deep learning can be used alongside traditional mathematical and geometrical models to unlock a new level of performance in spatial machine perception. The main capabilities I work on are realtime simulation, capture and understanding of 3D scenes.

My technical research contributions can be divided into three areas:

  1. generative models for learning compact and interpretable representations of the world
  2. optimization techniques for efficienct and robust inference
  3. photorealistic rendering and simulation systems
Simulation
Reconstruction
Understanding


Updates

Jun 20, 2021 Serving as an Area Chair for BMVC’21
May 1, 2021 CVPR’21 Outstanding Reviewer Award
Dec 10, 2020 ACCV’20 Outstanding Reviewer Award
Nov 7, 2020 Organizing a tutorial on 3D reconstruction and segmentation at 3DV’2020
Oct 10, 2020 Invited talk at MILA/REAL Robot Learning Seminar series: video
Jun 10, 2020 CVPR’20 Outstanding Reviewer Award
Jul 1, 2019 Invited Talk at the BMVA technical meeting on Geometry and Deep Learning.
Mar 1, 2019 Our 2nd Workshop on Deep Learning for Visual SLAM will be held at ICCV’19!
Dec 1, 2018 Co-organizing the CVPR’19 Workshop on Deep Learning for Visual Semantic Navigation
Jun 1, 2018 CVPR’18 Best Paper Honourable Mention Award

Selected Publications

  1. CVPR
    CodeSLAM-Learning a Compact, Optimisable Representation for Dense Visual SLAM
    Bloesch, Michael, Czarnowski, Jan, Clark, Ronald, Leutenegger, Stefan, and Davison, Andrew J
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
    arXiv
  2. ECCV
    Learning to Solve Nonlinear Least Squares for Monocular Stereo
    Clark, Ronald, Bloesch, Michael, Czarnowski, Jan, Leutenegger, Stefan, and Davison, Andrew J.
    In Proceedings of the European Conference on Computer Vision (ECCV) 2018
    arXiv
  3. AAAI
    VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem
    Clark, Ronald, Wang, Sen, Wen, Hongkai, Markham, Andrew, and Trigoni, Niki
    In AAAI Conference on Artificial Intelligence 2017
    arXiv
  4. Thesis
    Visual-inertial odometry, mapping and re-localization through learning
    Clark, Ronald
    University of Oxford
    PhD Thesis
     2017
    PDF
  5. CVPR
    Vidloc: A deep spatio-temporal model for 6-dof video-clip relocalization
    Clark, Ronald, Wang, Sen, Markham, Andrew, Trigoni, Niki, and Wen, Hongkai
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
    arXiv