Hacker News Reader

But if we know what a car ought to look like in 3D, can't we take the one photo we have from one direction and just fill in the blanks with that a priori 3D knowledge?

View on HN

Similar to how GPT-3 can be applied not only to create Text, but also fill in missing pieces of Images (ie. complete the missing half of a face).

Would the logical next step, use GPT-3 to create a 3D world? :)

GPT-3D rolls off the tongue nicely

Getting there. This is one part of the puzzle: https://arxiv.org/pdf/2007.11965

Reply on news.ycombinator.com