Depth of field
Model
Encoder Takes an input image and generates a high-dimensional feature vector Decoder Takes a high-dimensional feature vector and generates a semantic segmentation mask There are 3 major building blocks: Convolution Down-Sampling Up-Sampling
The encoder in the network computes progressively higher-level abstract features as the receptive fields in the encoder increase with the depth of the encoder. The spatial resolution of the feature maps is reduced progressively via a down-sampling operation, whereas the decoder computes feature maps of progressively increasing resolution via un-pooling (Zeiler and Fergus, 2014) or up-sampling
Examples
In this example, we will show how can we blur part of the background and emphasize the foreground. Starting with the original image:
We are calculating depth map and converting it into grayscale:
Based on the given threshold we extract the foreground and inverted mask
This helps us to make foreground image with transparent background: 
When we concatenate this image with blured version of original image:
We get the end result and original below it:
Coffe time
Let’s schedule a virtual coffee and see how you can learn or educate more efficiently.
Cofee time
Feel free to ask anything that might be of interest to you related to the courses and registration. We would gladly listen to you and try to help.
Your email
Your full name
Your question
It's totally free
iamai.academy is redefining education with unconventional and highly practical approach to knowledge delivery.