Machine learning is awesome for “soft” problems like language processing. But when it comes to problems that have exact solutions (like, say, path tracing denoising), maybe I’m just old-fashioned, but ML strikes me as an unfortunate hack…
-
Show this thread
-
Replying to @pcwalton
For production CG, ML denoising trained on the particular scene assets in use can work well. A hand-wavey defense is that it provides priors for better estimating the integrals from the samples you can afford. It biases the result but hopefully in a helpful direction
1 reply 0 retweets 1 like
Replying to @brettlevin
Yeah…I know it works, but I wish we could solve the problems more holistically…
9:22 PM - 14 Nov 2018
0 replies
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.