Conversation

Wild paper synthesizes photorealistic imagery for corresponding video game footage, roughly via a generator informed by extracted semantic scene info and a discriminator minimizing differences vs. photographic dataset. intel-isl.github.io/PhotorealismEn

0:07

8.9K views

189

This summary by

gives a nice overview with lots of comparisons. Also suggests an interesting possible future for this work—that photorealistic game engines could become very simple, emitting coarse scene info rather than complete renders.

youtube.com

Intel's Video Game Looks Like Reality!

Check out Perceptilabs and sign up for a free demo here: https://www.perceptilabs.com/papers

The paper "Enhancing Photorealism Enhancement" is available...

"Humans Are Amazing"

@shancarter

Jun 5, 2021

Would each run through on the racing course produce slightly different details? If you made slightly different paths early on, would the trees on the hills be different? Each choice you made might affect the render?

Andy Matuschak

@andy_matuschak

Replying to

@shancarter

Conceptually, yes. Frames are fully independent, though, so there's a similar issue temporally, which (unlike the prior work reviewed) this method seems to handle surprisingly well.

7:05 PM · Jun 5, 2021Twitter Web App

Replying to

Was just excited by the creative freedom from the idea that small choices early on by the player could lead to a huge variety of realistic and temporally consistent worlds (was not a criticism of the method at all!)

"Humans Are Amazing"

@shancarter

Jun 5, 2021

Guess I was just imagining AI dungeon but for racing games.

Replying to

youtube.com/results?search