HackerTube.dev

Eulerian Video Magnification

Miki Rubinstein · 787.9K views · 2012-05-23 · 4:28

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

The video accompanying the SIGGRAPH 2012 paper on Eulerian Video Magnification. It amplifies subtle changes in ordinary video, such as skin color shifts from a heartbeat, to reveal pulse and tiny motions.

On Hacker News

Cited as the canonical demonstration of pulling out invisible signals like pulse from video, with commenters imagining other applications.

Discussed on HN; no positive recommendation is recorded in this export · HN mentions 2012–2018

Topics

Computer vision, speech & NLPComputer graphics & rendering
Search by tags
eulerian video magnificationsiggraphcomputer visionpulse detectionmit csail

What people said

lowdest · 2018-01 · Reference

>What can we hack together that can be used to filter seizures? I think a video filter could do this. See this video on Eulerian Video Amplification from SIGGRAPH 2012: [VIDEO] A similar technique to reduce the amplitude of strobing seems plausible.

Read the original HN comment ↗
titojankowski · 2017-06 · Reference

Reminds me of those visualizations designed for magnifying tiny changes, Eulerian Video Magnification: [VIDEO] Perhaps a potential application?

Read the original HN comment ↗
raverbashing · 2015-06 · Reference

I remember a similar technique (maybe it's from the same people) where they amplified color changes. So the tiny flushes caused by the heartbeat were clearly visible [VIDEO] (from 1m30s)

Read the original HN comment ↗

Sources

Video by Miki Rubinstein, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Topic keywords do not match
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources