hackertube.io

AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215

Two Minute Papers · explainer · Watch on YouTube

Computer graphics & renderingMachine learning & deep learning

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.

Why Hacker News recommends it

Cited as an accessible explanation of AI denoising, which underpins real-time ray tracing on RTX hardware.

  • 2 people recommended it
  • 2 different months
  • 0 strong recommendations
  • first 2018, last 2019

What HN commenters said

  1. “Disney actually does a lot of research combining the world of graphics with deep learning.”

    Neural noise filtering for photorealistic rendered video.

    halflings, 2018-06 · Recommendation · in “Neural scene representation and rendering”

  2. “Two Minute Papers did a nice explanation of it”

    Nice explanation of NVIDIA's recurrent denoising autoencoder.

    jonas21, 2019-09 · Recommendation · in “Ray Tracing Denoising”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: denoising, path tracing, autoencoder, nvidia, real-time rendering

Also recommended by the same people