[visionlist] Postdoctoral Research Assistant in Computer Vision at the University of Oxford

Victor Adrian Prisacariu victor at viprad.net
Tue Sep 3 12:46:24 -04 2019

Postdoctoral Research Assistant in Computer Vision
Department of Engineering Science, Parks Road, Oxford

We are seeking an experienced full-time Postdoctoral Research Assistant in
Computer Vision to join Professor Victor Adrian Prisacariu’s research group
at the Department of Engineering Science (central Oxford). This post is
fixed-term for 2 years. The group is an internationally leading research
group that has numerous scientific awards and has close links with some of
the top industrial research labs.

This is a bleeding-edge research project that aims to link 3D object
reconstruction using SfM and/or depth fusion with 3D deep learning, with a
strong focus on accuracy. Lambertian-constrained approaches have shown
that, given enough sensor data, the visible shape of 3D objects can be
recovered quickly and with high accuracy. At the same time, deep learning
has become the go-to strategy for visual tasks such as object detection and
recognition. Small steps have already been taken towards augmenting
geometric 3D reconstruction with deep learning, but the focus is often on
simple objects and coarse accuracy. This project aims to dramatically
increase the accuracy of the reconstructions, while, at the same time,
addressing some of the most difficult corner cases in 3D reconstruction
(e.g. transparent objects). Importantly, the work is to be done jointly
with a renowned industrial partner and is likely to see widespread adoption
in society.

You should possess a doctorate, or be near completion of a doctorate, in
computer vision or machine learning, together with a
strongcvnet at mail.ewind.com publication record at principal computer vision
conferences (CVPR, ECCV, ICCV and BMVC), with a background 3D geometry
(depth fusion/SLAM/object tracking and reconstruction) and/or deep learning.

Informal enquiries may be addressed to victor at robots.ox.ac.uk.
To apply, or for more information, visit

Only applications received before 12.00 midday on Thursday 12 September
2019 can be considered.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20190903/d1e793c7/attachment.html>

More information about the visionlist mailing list