Learning low-level vision Computer Examples by Michael Ross
Learning low-level vision
Feb 25, 2016
Computer Examples by Michael Ross. Learning low-level vision. Ising model. Each location has a 50% chance of being 'up' or 'down'. There is a 60% chance that a location has the same value as one of its 8-connected neighbors. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Learning low-level vision
Computer Examples
by Michael Ross
Ising model● Each location has a 50% chance of being 'up'
or 'down'.● There is a 60% chance that a location has the
same value as one of its 8-connected neighbors.
● There is an 80% chance that the sensor at a location reports the correct spin.
Ising model
True scene. Noise corrupted. Reconstructed.
Ising model with Gaussian noise
True scene. Noise corrupted. Reconstructed.
Learned optical flow
Learned optical flow
Learned optical flow
Super-resolution
Super-resolution
Super-resolution
Super-resolution
Super-resolution
Segmentation● An attempt to learn segmentation rules from
examples.● Learn sensor models for each feature.● Construct an MRF with interconnected layers,
one for each feature.● Allow individually insufficient features to
exchange information.
Segmentation
Signal: horizontal & verticalgradients.
Scene: edge detected bymotion.
Segmentation
...
Segmentation
Signal: horizontal & verticalgradients.
Scene: edge detected bybelief propagation.
Segmentation● Issues: takes about 25 minutes to produce
result (10 iterations). Why? Considers 100 possible candidates at each location -> ~36 million calculations per iteration.
● Simple features are not very predictive at many locations - better features mean that we need to consider fewer candidates.
● Benefit: learning reduces the number of assumptions and preconceptions.
Related Documents
