3D Shape Generation is still one of these problems that are much less solved than 2D image generation. There aren't great data sets or tons of, there's not tons of like sketches and 3D shapes that correspond to those sketches. Once you can turn your sketch into embeddings in a model, now essentially it lives in a plane that is comparable to the plane where you're getting data from other sources, other images. So functionally, you're almost leveraging what the model has learned by looking at like images, like photographs of things,. except you're using that information to have it create a representation of your sketch.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode