Geometric Optimisation in Computer Vision

Reconciling noisy and outlier-prone measurements with mathematical (in particular, geometric) models is a recurrent task in science and engineering. It is also often an unavoidable step in many computer and robotic vision pipelines. In this talk, I will provide an overview of the long line of research in this area, particularly on the algorithmic aspects, culminating in the major results that my team and I have achieved more recently. I aim to impress upon the audience interesting fundamental structures of the problem, which can hopefully stimulate discussion and inspiration to relevant research areas. The incorporation of recent advances in machine learning into geometric optimisation, as well as novel formulations of the problem inspired by commercial applications, will also be highlighted.


Tat-Jun Chin received his PhD in computer systems engineering from Monash University in 2007, which was supported by the Endeavour Australia-Asia Award. He is currently an Associate Professor at The University of Adelaide, and a Chief Investigator of the Australian Centre for Robotic Vision (ACRV), and the Director for Machine Learning for Space at The Australian Institute for Machine Learning (AIML). Tat-Jun is an Associate Editor of the IPSJ Transactions on Computer Vision and Applications (TCVA) and Journal of Imaging (J. Imaging). Tat-Jun's research interest lies in optimisation for computer vision and machine learning, and their application to AI, robotics, mining and space engineering. He has published more than 90 research articles on the subject, and has won several awards for his research, including a CVPR award (2015), a CVPRW award (2019), a BMVC award (2018), two DST Awards (2015, 2017), and a Best of ECCV (2018) special issue invitation. Recently, his team won the Kelvins Pose Estimation Challenge organised by the Advanced Concepts Team of the European Space Agency.


Date & time

11.30am–12.30pm 30 Sep 2019


Room:Graduate Teaching Room (221)


Dr Tat-Jun Chin


02 6125 2394

Updated:  10 August 2021/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing