,
10 tweets,
8 min read
Read on Twitter
I used @runwayml to reconstruct this scene from The Last Jedi by having DeepLab recognize all the objects in each frame, and then having SPADE try to paint the original frame from the objects.
@runwayml More on the reconstruction process here: aiweirdness.com/post/186539822…
This is the first step, where DeepLab segments an image into objects. "Lightsaber" is not a category it has, so it improvises.
This is the first step, where DeepLab segments an image into objects. "Lightsaber" is not a category it has, so it improvises.
@runwayml Next, SPADE has to paint a picture just from DeepLab's labeled image. It sees person with a baseball bat, so it looks a lot like it tried to paint Luke in a baseball jersey.
@runwayml Here's another scene from TLJ as segmented by DeepLab (which sees people with teddy bears hiding behind the rock) and SPADE (which dutifully has to draw the teddy bears)
@runwayml I like this sequence. DeepLab didn't detect the lightsabers & decided the ground was snow. (And also a surfboard). Trying to recover the original image, SPADE looked at all the snow & decided to put Luke and Kylo in snowsuits.
@runwayml I'm really excited to see what these will look like as segmentation & reconstruction get better. Could one segment a scene from Pride and Prejudice and replace all the "human" labels with "bear"? Or "refrigerator"?
@runwayml Here's a cool variation where @jonathanfly gives SPADE not a DeepLab segmentation but frames from cartoons or 8-bit video games.
@runwayml @jonathanfly i love this!
