Copy

Welcome to your

AI Weekly Digest

presented by Louis (What's AI) Bouchard

1️⃣ Manipulate Images with Blobs! BlobGAN Explained

 

BlobGAN allows for unreal manipulation of images, made super easily controlling simple blobs. All these small blobs represent an object, and you can move them around or make them bigger, smaller, or even remove them, and it will have the same effect on the object it represents in the image. This is so cool!

As the authors shared in their results, you can even create novel images by duplicating blobs, creating unseen images in the dataset like a room with two ceiling fans! Correct me if I’m wrong, but I believe it is one of, if not the first, paper to make the modification of images as simple as moving blobs around and allowing for edits that were unseen in the training dataset. 

And you can actually play with this one compared to some companies we all know! They shared their code publicly and a Colab Demo you can try right away. Even more exciting is how BlobGAN works... Read more here.

Watch the video

2️⃣ AI Ethics with Lauren

If you thought Blob Opera was the only blob-based AI, think again!

What I really like about this model is that the blobs provide a level of transparency and intuition that many AI models lack. The mid-level representation helps bridge the gap between pure numbers and pure images. This might be a good tool to teach kids about AI, introducing two approaches in tandem so that both can be understood in a single example. It provides much needed accessibility for a model of this level!

Aside from a lack of exercise from not moving the furniture yourself, the biggest concern I could see resulting from BlobGAN is mainly an aesthetic one. Like many Western-created AI models, this is hyper-culturally specific to the mainstream interior design of a traditional Western palette, given the training data it was supplied with. I worry this may create an artistic overreliance on AI-generated interior spaces.  Style is more than furniture placement and size, and certainly more than Pottery Barn-esque bedrooms. I worry about the artistry of untraditional living being lost if this becomes mainstream enough to influence at scale. Given that this research partially comes from Adobe, makers of Creative Suite, that is certainly a possibility.

To remedy this concern, BlobGAN would need to be trained on other interiors to use in other contexts, which wouldn’t be too big of an undertaking since this is unsupervised and the data would not have to be labeled. I’m sure this is on the agenda for the future and I’m excited to see how it would perform on other scene representations. Just don’t be afraid to break the mold when designing your space, no matter what AI shows you!


- AI Ethics segment by Lauren Keegan
Want to get into AI or improve your skills? Click here!
We are already at the end of this AI weekly digest! Thank you for thoroughly going through this iteration! I hope you enjoyed it. 

If you have suggestions, comments, or other thoughts, you can reach me by replying to this email or directly on Twitter or Linkedin. Don't hesitate to come to chat with more than 20'000 AI enthusiasts on Discord!
I hope the next week wipes away some of your stress and brings new opportunities, challenges and happiness. A happy new week from your friend!

If you would like to support my work financially, you can become a Patreon and receive a cool role in the discord server at the same time!

Share the knowledge and forward this email to a friend using this link: http://eepurl.com/huGLT5

- Louis Bouchard
Blog
Twitter
LinkedIn
GitHub
Email
Copyright © 2022 What's AI, All rights reserved.


Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

Email Marketing Powered by Mailchimp