Background Matte Generation Using Novel Neural Architecture

 Generating background mattes for video is something that tends to be used for all kinds of different applications.  There is a long history of different techniques for this, like color key which assumes the foreground objects or people are in front of a flat color background (think green screen).  Or one of the many Siggraph papers over the years focused on different variants of this (graph-cut, etc).

With the deep learning neural net renaissance currently taking place, you would expect to see different neural net implementations of this.  Nvidia recently announced an implementation for example. And now the U of Washington graphics lab has come up with an interesting neural net based approach.  Take a look at the video examples below.



The neural net architecture they use is interesting, and if you stretch your brain you might start to come up with other applications of the basic idea. Two different neural nets are used.  A low res one to get in the ballpark, and then a high res one that is based on patches (and we've seen that idea before in generative models) that refines detail in hard to matte areas.

You do need an image of the background without the foreground objects for thi to work. So my question is whether you could manually cut the foreground out, then use a different neural net algorithm to in-paint, then use the in-painted image as the background image for the matting algorithm.

You can access the project page here.

There is a github page with code to check out here.

And of course there is a paper here.

When you read the paper you will note the skip connections in the encoder-decoder stages, which is a theme in so much of the recent generative nets we have featured here at HTC.  They based the backbone of the encoder on ResNet-50.

The decoder used bilinear up-sampling for each 'build it back up' step, then concatenate with skip connection from encoder, followed by 3x3 convolutional layer, batch normalization layer, and ReLU.

Comments

Post a Comment

Popular posts from this blog

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Image
 Like the Doublemint Twins touting the joys of Doublemint gum, 2 GANs are surely better than 1 GAN.  Especially if we package them together inside of one meta GAN module.  And this is exactly what the CycleGAN architecture does. Have you ever harbored dark secrets of turning a horse into a zebra?  The CycleGAN was developed to do just that. Learn how to turn a horse into a zebra.  And more. Now right away you can notice a difference between the image to image transformation GAN architectures we've been discussing over the last few posts.  Those last few posts described systems that learn from a database of matched input-output image pairs. And if your goal is to turn an edge representation into a nicely filled in continuous tone image, it's easy to build your database of matched input-output image pairs that your GAN system can then learn off of.  Take a continuous tone image (which will be the output of the database pair entry), then run it through an edge detector algorithm. 
Read more

Pix2Pix: a GAN architecture for image to image transformation

Image
 I thought following up yesterday's TraVelGAN post with a Pix2Pix GAN post would be useful to compare what is going on in the 2 architectures.  Two different approaches to the same problem. I stole this Pix2Pix Overview slide below from an excellent deeplearning.ai GAN course (note that they borrowed it from the original paper) because it gives you a good feel for what is going on inside of the Pix2Pix architecture.    Note how the Generator part is very much like an auto-encoder architecture, but rebuilt using the U-Net architecture features (based on skip-connections) that fastai has been discussing in their courses for several years before it became more widely known to the deep learning community at large  (and which originally came from an obscure medical image segmentation paper) . So the Generator in this Pix2Pix GAN is really pretty sophisticated, consisting of a whole image to image auto-encoder network with U-Net skip connections to generate better image quality at highe
Read more

Smart Fabrics

Image
"What makes smart fabrics revolutionary is that they have the ability to do many things that traditional fabrics cannot, including communicate, transform, conduct energy and even grow."  This is a quote from Rebeccah Pailes-Friedman, who is a professor at Pratt with a research focus on developing wearable technology and smart textiles. Enhancing textiles can be viewed through different lens.  Enhancements can be aesthetic, or performance boosting, or durability boosting. 
Read more