jonas21Sep 2019Recommends
It's only briefly mentioned, but NVIDIA's recurrent denoising autoencoder is pretty amazing. [link] Two Minute Papers did a nice explanation of it: ▶ this video
in “Ray Tracing Denoising” · View on HN
AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215 on HackerTube: recommended by 2 Hacker News commenters across 2 separate months, 2018–2019.
Two Minute Papers
Open on YouTubeexplainer · dated
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.
Why Hacker News recommends it
Cited as an accessible explanation of AI denoising, which underpins real-time ray tracing on RTX hardware.
- people recommended it
- 2
- separate months
- 2
- strong recommendations
- 0
- discussed on HN
- 2018–2019
“Two Minute Papers did a nice explanation of it”
What HN commenters said
5 Hacker News comments link this video. Each one links back to its thread.
halflingsJun 2018Recommends
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] ▶ this video
in “Neural scene representation and rendering” · View on HN
kuzehankaMar 2019Cites it
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. ▶ this video
in “Quake II RTX: Re-Engineering a Classic with Ray Tracing Effects on Vulkan” · View on HN
blooopDec 2018Cites it
This uses a neural network ▶ this video video results start around 1:15 This one does not use a neural network: [link]
in “Path Tracing vs. Ray Tracing (2016)” · View on HN
scrumptionAug 2018Cites it
I don't think your estimations take into account the massive gains from AI denoising techniques such as ▶ this video
in “Nvidia announces RTX 2000 GPU series with ‘6x more performance’ and ray-tracing” · View on HN
Topics & tags
Computer graphics & renderingMachine learning & deep learningdenoisingpath tracingautoencodernvidiareal-time rendering