The more high level you get, the more it's really beneficial to join reasoning and end to end using neural networks. You can have a deep network that is not only reasoning about a single image but it's reasoning about a video of images as well. Or you can have two separate ones kind of one that's focused on pixels and one that'sfocused on 3D understanding from those representations. There's just really valid arguments for bunch of different approaches I would say.

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