Duration: 2:10

57,529 views

332

We present a new interactive approach to 3D scene understanding. Our system, SemanticPaint, allows users to simultaneously scan their environment, whilst interactively segmenting the scene simply by reaching out and touching any desired object or surface. Our system continuously learns from these segmentations, and labels new unseen parts of the environment. Unlike offline systems, where capture, labelling and batch learning often takes hours or even days to perform, our approach is fully online.

Read the paper:
http://research.microsoft.com/en-US/projects/semanticpaint/valentin2015semanticpaint.pdf

Main Contacts:
Shahram Izadi, Microsoft Research: shahrami@microsoft.com
Interactive 3D Technologies, Microsoft Research:
http://research.microsoft.com/en-us/groups/i3d/

Philip Torr, University of Oxford: philip.torr@eng.ox.ac.uk
Torr Vision Group, University of Oxford:
http://www.robots.ox.ac.uk/~tvg/