AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Two Minute Papers2 HN recommenders · recommended in 2 months, 2018–2019
explainer · general · 2018–2019 on HN
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.
Up next
3 mo on HNThe Backwards Brain Bicycle - Smarter Every Day 133
SmarterEveryDay
4 HN recommender · 2015–2025
2 mo on HNProject Starline: Feel like you're there, together
Google
2 HN recommender · 2021–2024
9 mo on HNHow Crash Bandicoot Hacked The Original Playstation | War Stories | Ars Technica
Ars Technica
13 HN recommender · 2020–2026
4 mo on HNThe Road to PS5
PlayStation
6 HN recommender · 2020–2023
5 mo on HNTensorflow and deep learning - without a PhD by Martin Görner
Devoxx
6 HN recommender · 2017–2020
13 mo on HNThe Beauty of Bézier Curves
Freya Holmér
16 HN recommender · 2021–2026
11 mo on HNThe Continuity of Splines
Freya Holmér
10 HN recommender · 2022–2026
10 mo on HNelevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)
Demoscene High-Quality Videos (Annikras)
7 HN recommender · 2013–2025
10 mo on HNPainting a Character with Maths
Inigo Quilez
13 HN recommender · 2021–2025
10 mo on HNThe Real Story Behind Wayland and X - Daniel Stone (linux.conf.au 2013)
Mladen Mijatov
13 HN recommender · 2013–2026
9 mo on HNA Deep Dive into Nanite Virtualized Geometry
SIGGRAPH Advances in Real-Time Rendering
7 HN recommender · 2021–2026
10 mo on HNSiggraph2019 Geometric Algebra
Bivector
8 HN recommender · 2020–2022
5 comments from Hacker News
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
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
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
This uses a neural network ▶ this video video results start around 1:15 This one does not use a neural network: link
I don't think your estimations take into account the massive gains from AI denoising techniques such as ▶ this video