AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Two Minute Papers2 HN recommenders · 2018–2019
65K views · explainer · dated · Uploaded 2017-12-17
A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences. It shows how a neural network can produce usable renders from very few samples.
Cited as an accessible explanation of AI denoising, which underpins real-time ray tracing on RTX hardware.
2:25:52The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
18:40But what is a neural network? | Deep learning chapter 1
3Blue1Brown
24:26The Beauty of Bézier Curves
Freya Holmér
1:13:50The Continuity of Splines
Freya Holmér
3:36elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)
Demoscene High-Quality Videos (Annikras)
1:30:28AlphaGo - The Movie | Full award-winning documentary
Google DeepMind
27:14Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown
24:46Painting a Character with Maths
Inigo Quilez
5 comments from Hacker News
Disney actually does a lot of research combining the world of graphics with deep learning. Some examples that you might appreciate (from the excellent channel "Two Minute Papers"): . "Disney's AI Learns To Render Clouds" [0] . "AI Learns Noise Filtering For Photorealistic Videos" [1] [0] [LINK] [1] [VIDEO]
I don't think your estimations take into account the massive gains from AI denoising techniques such as [VIDEO]
This uses a neural network [VIDEO] video results start around 1:15 This one does not use a neural network: [LINK]
Deep learning denoiser. I don't know if NVIDIA came up with some marketing term for it. It's what allows RTX to produce meaningful images at all despite the renderer running at 0.5-2 samples per pixel which looks little better than random noise. I kind of assumed they'd call it DLDN because they called their deep learning supersampling DLSS. I guess not, go figure. [VIDEO]
It's only briefly mentioned, but NVIDIA's recurrent denoising autoencoder is pretty amazing. [LINK] Two Minute Papers did a nice explanation of it: [VIDEO]