Skip to content
HHackerTube.videoSurprise me

3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013

3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013 on HackerTube: recommended by 2 Hacker News commenters across 2 separate months, 2013–2024.

Daniel CohenOr

demo · intermediate · dated

Open on YouTube

A SIGGRAPH Asia 2013 research demo of 3-Sweep, a tool for extracting editable 3D objects from a single photo using a few user strokes. It predates modern AI image tools.

Why Hacker News recommends it

HN recalls it as a mind-blowing pre-AI demo of 2D-to-3D object extraction.

people recommended it
2
separate months
2
strong recommendations
1
discussed on HN
2013–2024
“this single video blew my mind back in *2013* and I find myself thinking about it often.”
— alfiedotwtf, Oct 2024, in “Adobe's new image rotation tool is one of the most impressive AI tools seen”

What HN commenters said

5 Hacker News comments link this video. Each one links back to its thread.

alfiedotwtfOct 2024Strongly recommends

SIGGRAPH from over a decade ago has entered the chat... ▶ this video It may not be AI, but this single video blew my mind back in *2013* and I find myself thinking about it often.

in “Adobe's new image rotation tool is one of the most impressive AI tools seen” · View on HN

cookingrobotSep 2013Recommends

I would love to see this combined with object extraction to make 3d models from the measurements. Here's an amazing demo: ▶ this video

in “Show HN: 3D sensing SDK for iOS – Produces point cloud and 6DOF device motion” · View on HN

leviathantOct 2024Cites it

>SIGGRAPH from over a decade ago has entered the chat... > > ▶ this video A version of this was available in Photoshop for a long time, but I think the feature was deprecated and removed completely this year. I had used it for a few things here and there, but dedicated 3D tools were much better if you were working in that space.

in “Adobe's new image rotation tool is one of the most impressive AI tools seen” · View on HN

trendiaOct 2016Cites it

That is correct. Sometime in the future, consumers will have software that can turn 2D images into simulated 3D [0]. It's still in dev mode right now, though. [0] ▶ this video

in “Virtual Forest” · View on HN

carlosdpJul 2016Cites it

Lots of interesting research being done on this, keep an eye out for stuff from SIGGRAPH later this month. Here's an example from SIGGRAPH Asia: ▶ this video .

in “HTC Vive Headset Nearing 100,000 Sales” · View on HN

Topics & tags

Computer vision, speech & NLPComputer graphics & rendering3d modelingsiggraphcomputer visionimage editingresearch demo