search

sergeytulyakov / mocogan

MoCoGAN: Decomposing Motion and Content for Video Generation
573 stars 113 forks source link

Could the code for generating the shape motion dataset also be released? #10

Closed Dawn90 closed 6 years ago

Dawn90 commented 6 years ago

Hello, This is such a nice job. The codes are clean and easy to follow. Recently, I'm working on video disentangling. Could I have the code for generating the shape motion dataset? Thanks a lot! Dong

sergeytulyakov commented 6 years ago

Hello,

At this point there are no plans to release this code. But it's quite easy.

  1. Randomly sample content (shape, color, size, initial position)
  2. Randomly sample several anchor points for the Bezier curve
  3. Compute Bezier curve
  4. Draw the shape along the curve