One Day Meeting: 3D worlds from 2D images in humans and machines.
Wednesday 29 January 2020
Chairs: Andrew Schofield, Aston University. Richard Bowden, University of Surrey. Wendy Adams University of Southampton.
Keynote Speaker
James Elder. Professor of Human and Computer Vision, York University, Toronto. Johannes Burge, University of Pennsylvania Lourdes Agapito, University College London.
Videos of Talks
On our BMVA YouTube channel there are recorded talks of the slides and speaker from the day here
Programme
When humans view a photograph they perceive the 3D world that constructed the image. They can, for example, describe the depth relationships between objects, plan a route through the scene and imagine the scene from a different viewpoint. This process is automatic and compulsive. For example, even though humans possess size constancy they will readily misinterpret the size of a person in order to make sense of the rest of the scene as a 3D world. State of the art computer vision systems are now also very good at reconstructing 3D layout from 2D images (3D uplift) although, unlike humans, this is often restricted to specific domains or requires multiple views. This workshop will consider recent developments in 3D uplift as well as our current knowledge of scene understanding in human vision.
10:00 - Registration and Coffee
10:30 - Andrew Schofield, Aston University, Welcome and Introduction
10:35 - Wendy Adams, University of Southampton, The Southampton & York Natural image Dataset
10:45 - Keynote talk James Elder, York University, Canada
11:30 - Rebecca Lawson, University of Liverpool, Size perception for real, 3D objects and for 2D images on a specified plane
11:50 - Paul Linton, City, University of London, Does Human Vision Triangulate Absolute Distance?
12:10 - Brian Rogers, University of Oxford, 3D worlds from 2D images: a mistaken conception
12:30 Lunch
13:30 - Keynote talk Johannes Burge, University of Pennsylvania
14:20 - Dhanraj Vishwanath, University of St Andrews, What constitutes the perception of pictorial depth?
14:40 - Robert Black, RealSpace, ‘Paradoxical’ Bi-Ocular Stereoscopy - 25 years on
15:00 – Coffee
15:20 Keynote talk Lourdes Agapito, University College London.
16:10 Will Smith, University of York, Self-supervised shape from shading and inverse rendering in the wild
16:30 Oisin Mac Aodha, University of Edinburgh, Digging into Monocular Depth Estimation
A copy of the Programme can be found here.
Meeting Location
The BCS moved in September, the meeting will take place at:
British Computer Society (BCS), 25 Copthall Avenue, London EC2R 7BP