Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
cvpr16_tutorial [2016/07/06 12:09]
awf
cvpr16_tutorial [2017/02/20 15:11] (current)
awf
Line 8: Line 8:
 <​html><​h2><​a href="​http://​www.cs.toronto.edu/​~jtaylor">​Jonathan Taylor</​a>,​ <a href="​http://​www.perceptiveio.com">​PerceptiveIO</​a></​h2></​html>​ <​html><​h2><​a href="​http://​www.cs.toronto.edu/​~jtaylor">​Jonathan Taylor</​a>,​ <a href="​http://​www.perceptiveio.com">​PerceptiveIO</​a></​h2></​html>​
  
-Slides: {{:​cvpr_2016_b.pdf|PDF (16MB)}} {{:​cvpr_2016_b.pptx|PPTX (385MB)}}+Slides: {{:​cvpr_2016_b.pdf|PDF (16MB)}} {{:​cvpr_2016_b.pptx|PPTX (385MB)}} {{https://​github.com/​awf/​OpenSubdiv-Model-Fitting|GitHub}}
  
 In vision and machine learning, almost everything we do may be considered to be a form of model fitting. Whether estimating the parameters of a convolutional neural network, computing structure and motion from image collections,​ tracking objects in video, computing low-dimensional representations of datasets, estimating parameters for an inference model such as Markov random fields, or extracting shape spaces such as active appearance models, it almost always boils down to minimizing an objective containing some parameters of interest as well as some latent or nuisance parameters. ​ This tutorial will describe several tools and techniques for solving such optimization problems, with a focus on fitting 3D smooth-surface models, such as subdivision surfaces, to 2D and 3D data.  In vision and machine learning, almost everything we do may be considered to be a form of model fitting. Whether estimating the parameters of a convolutional neural network, computing structure and motion from image collections,​ tracking objects in video, computing low-dimensional representations of datasets, estimating parameters for an inference model such as Markov random fields, or extracting shape spaces such as active appearance models, it almost always boils down to minimizing an objective containing some parameters of interest as well as some latent or nuisance parameters. ​ This tutorial will describe several tools and techniques for solving such optimization problems, with a focus on fitting 3D smooth-surface models, such as subdivision surfaces, to 2D and 3D data.