AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Why Hacker News recommends it
Cited as an accessible explanation of AI denoising, which underpins real-time ray tracing on RTX hardware.
What it is
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.
Recommended by 2 HN commenters across 2 different months, 2018 to 2019.
What Hacker News said
Recommends halflings · 2018-06 · on “Neural scene representation and rendering”
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]
Recommends jonas21 · 2019-09 · on “Ray Tracing Denoising”
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]
Cites scrumption · 2018-08 · on “Nvidia announces RTX 2000 GPU series with ‘6x more performance’ and ray-tracing”
I don't think your estimations take into account the massive gains from AI denoising techniques such as [this video]
Cites blooop · 2018-12 · on “Path Tracing vs. Ray Tracing (2016)”
This uses a neural network [this video] video results start around 1:15 This one does not use a neural network: [LINK]
Cites kuzehanka · 2019-03 · on “Quake II RTX: Re-Engineering a Classic with Ray Tracing Effects on Vulkan”
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]