Eulerian Video Magnification
Miki Rubinstein0 HN recommenders · 2012–2018
788K views · demo · evergreen · Uploaded 2012-05-23
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.
Cited as the canonical demonstration of pulling out invisible signals like pulse from video, with commenters imagining other applications.
24:26The Beauty of Bézier Curves
Freya Holmér
1:13:50The Continuity of Splines
Freya Holmér
3:36elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)
Demoscene High-Quality Videos (Annikras)
24:46Painting a Character with Maths
Inigo Quilez
45:35The Real Story Behind Wayland and X - Daniel Stone (linux.conf.au 2013)
Mladen Mijatov
1:10:00A Deep Dive into Nanite Virtualized Geometry
SIGGRAPH Advances in Real-Time Rendering
1:37:22Siggraph2019 Geometric Algebra
Bivector
48:10Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
Google TechTalks
5 comments from Hacker News
Between Paul Ekman's work in behavioral science and detecting a persons pulse rate from video ( [VIDEO] ), it seems like one could have a pretty decent "lie detector" running on a smart phone.
"read your heartrate" reminded me of [VIDEO] (video to MIT paper submitted to SIGGRAPH about emphasizing video features, blood flow among them)
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)
Reminds me of those visualizations designed for magnifying tiny changes, Eulerian Video Magnification: [VIDEO] Perhaps a potential application?
>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.