Skip to content

Latest commit

 

History

History
21 lines (15 loc) · 563 Bytes

File metadata and controls

21 lines (15 loc) · 563 Bytes

Auto-Image-Completion

Tool designers and photographers can use it to fill in unwanted or missing parts of images.

  1. Interpreting images as samples from a probability distribution.

  2. Quickly generating fake images using Generative Adversarial Networks(GANs).

  3. Finding the best fake image for image completion.

Technology Stack:

Python
TensorFlow
Pandas
Numpy

To-Do

  1. Add screenshots of the work.
  2. Train the model on actual human photographs.

Future Scope

Make it auto complete any image(i.e., living as well as non-living)