Bio

I am a third year Ph.D. student at Imperial College London, advised by Prof. Andrew Davison. Previously, I completed my undergraduate and Masters in Physics at the University of Oxford.

My work is in computer vision and machine learning and specifically I work on building efficient scene understanding systems for robotics using graph-based algorithms. I'm also very interested in distributed training of deep networks, cellular automata and neural implicit representations.

News

August 2021
I'll be interning at Facebook AI Research with Mustafa Mukadam this autumn!
July 2021
iMAP accepted to ICCV!
July 2021
Check out our new distill style interactive introduction to GBP here.
June 2020
Attended CVPR 2020 virtual conference.
March 2020
Check out these interactive animations of Gaussian belief propagation to help get more of an intuition for the inference algorithm!
March 2020
Bundle Adjustment on a Graph Processor was accepted to CVPR 2020!
July 2019
Attended International Computer Vision Summer School (ICVSS) in Sicily.
July 2018
Beginning a 3 months research as a visiting student as MIT CSAIL with the ALFA group!
June 2018
Recieved the prize for best Masters Project in Astrophysics at Oxford for my research in Gravitational Wave Astronomy [pdf]!

Publications

Incremental Abstraction in Distributed Probabilistic SLAM Graphs
arXiv preprint 2021
Joseph Ortiz, Talfan Evans, Edgar Sucar, Andrew J. Davison
iMAP: Implicit Mapping and Positioning in Real-Time
ICCV 2021
Edgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. Davison
A visual introduction to Gaussian Belief Propagation
Self published / arXiv 2021
Joseph Ortiz, Talfan Evans, Andrew J. Davison
Bundle Adjustment on a Graph Processor
CVPR 2020
Joseph Ortiz, Mark Pupilli, Stefan Leutenegger, Andrew J. Davison
FutureMapping 2: Gaussian Belief Propagation for Spatial AI
arXiv 2019
Andrew J. Davison, Joseph Ortiz