My research interests lie at the intersection of 3D Computer Vision and Computer Graphics. My work focuses on how to bridge the gap between the real world and the digital world by creating photorealistic digital copies of reality. Some areas that I work on include:
- Neural Rendering: photorealistic reconstruction, novel view synthesis, appearance acquisition
- Dense Visual SLAM: 3D scene representations, state-estimation, numerical optimization
- Scene Understanding: 3D semantic segmentation, 3D object detection and tracking
I am particularly interested in developing novel 3D vision techniques that can be used to advance the state-of-the-art in applications such as Mixed Reality (AR/VR), Home Robotics and the Physical Sciences.
If you are interested in doing a DPhil related to these topics please email me.
I received my MSc in Information Engineering from the University of the Witwatersrand and my DPhil from the University of Oxford. From 2017 to 2020 I was a member of the Dyson Robotics Lab. I then held an Imperial College Research Fellowship, before joining the University of Oxford in 2022 as an Associate Professor. My research has received various accolades including a Best Paper Honourable Mention at CVPR in 2018.
Volumetric Bundle Adjustment for Online Photorealistic Scene Capture
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.
TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering
Martin Piala and Ronald Clark
In International Conference on 3D Vision (3DV). December, 2021.
Orientation Keypoints for 6D Human Pose Estimation
Martin Fisch and Ronald Clark
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). November, 2021.