My thesis will be online via Imperial College London's open access research repository, Spiral soon, but in the meantime, you can find it here.

I had a fantastic opportunity to visit many exciting companies and organisations in both S. Korea and Japan, especially to give a talk about our event-based SLAM technology at:

We've got the best paper award at ECCV 2016! Big congratulations to Stefan and Andy as well! :)

The Qualcomm Innovation Fellowship European champion and the best industry paper award at BMVC, both in 2014, and now this at one of the best computer vision conferences?! Today is the best day of my PhD life! :)

Honestly, without my supervisor Andy, it would not have been possible, so my special thanks goes to him!

Abstract:

We propose a method which can perform real-time 3D reconstruction from a single hand-held event camera with no additional sensing, and works in unstructured scenes of which it has no prior knowledge. It is based on three decoupled probabilistic filters, each estimating 6-DoF camera motion, scene logarithmic (log) intensity gradient and scene inverse depth relative to a keyframe, and we build a real-time graph of these to track and model over an extended local workspace. We also upgrade the gradient estimate for each keyframe into an intensity image, allowing us to recover a real-time video-like intensity sequence with spatial and temporal super-resolution from the low bit-rate input event stream. To the best of our knowledge, this is the first algorithm provably able to track a general 6D motion along with reconstruction of arbitrary structure including its intensity and the reconstruction of grayscale video that exclusively relies on event camera data.

Link to the paper:

Link to the video:

Link to the presentation: