The AI for Cooking
Create your own dish by selecting its type and its ingedients!
What type of dish?
What's on your plate?
Do you think this image is a real dish? (Leave us a feedback to skip the waiting time)
Kidding me? Not at all!
Not so real
Maybe, I can't tell
It seems real
It is so real!
Explore our existing gallery of dishes -- real versus synthetic!
Get a random dish!
Learn more about the AI behind CookGAN.
Synthesizing photo-realistic food meal images from textual descriptions of its ingredients.
The framework first builds an attention-based ingredients-image association model, which is then used to condition a generative neural network tasked with synthesizing meal images. Furthermore, a cycle-consistent constraint is added to further improve image quality and control appearance. Preliminary experiments show our model is able to generate meal image corresponding to the ingredients list.
Beyond its ability to help understand the relationship between two domains (i.e. natural languange and vision), a well trained model also has other applications, to name a few, Text visualization, Data augmentation, Cooking skill learning.
Samsung AI Center
Department of Computer Science
New Jersey, USA