Geometry and Deep Learning

One Day Meeting: Geometry and Deep Learning

Friday 19 July 2019

Chairs: Vassileios Balntas and Krystian Mikolajczyk

Keynote Speakers

Invited Talks:

Meeting Report

After the meeting the organisers prepare a short summary of the meeting. The report is available here.


Visual geometry is one of the areas where applying deep learning is less obvious than in other computer vision problems and has only just started to make an impact. In this meeting, we aim to explore the key challenges in addressing the geometry related tasks with end-to-end learning.

09:30-10:20 Keynote: Jiri Matas
10:20-10:40 Coffee Break
10:40-11:00 Ignas Budvytis: Large Scale Semantic Re-Localisation
11:00-11:00 Ronnie Clark: Deep Learning and Geometry: A Top-Down Approach
11:00-11:20 Armin Mustafa: Semantically Coherent 4D Scene Flow of Dynamic Scenes
11.20-11.40 Joao Miguel Vieira Cartucho: Data Augmentation with 3D CG for Surgical Vision
11.40-12.10 Invited talk: Daniyar Turmukhambetov & Michael Firman - Niantic Labs
12:10-13:10 Lunch
13:10-14:00 Keynote: Andrea Vedaldi
14:00-14:20 Jaime Spencer Martin: SAND: Feature Learning via Hierarchical Context Aggregation
14:40-15:00 Josh Harris: Learning to infer 3D pose from 2D examples
15.00-15.30 Invited Talk: Relja Arandjelović - Deepmind
15:30-15:50 Coffee Break
15:50-16:40 Keynote: Stefan Leutenegger

Videos of Talks

On our BMVA youtube channel there are recorded talks of the slides and speaker from the day here.

Meeting Report

After the meeting the organisers will prepare a short summary of the meeting.

Meeting Location

British Computer Society (BCS), 5 Southampton St, London WC2E 7HA