HackerTube

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

Daniel CohenOr2 HN recommenders · 2013–2024
2.3M views · demo · dated · Uploaded 2013-08-13

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.

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

Computer vision, speech & NLPComputer graphics & rendering

Watch on YouTube

5 comments from Hacker News

@cookingrobot2013 · in “Show HN: 3D sensing SDK for iOS – Produces point cloud and 6DOF device motion”

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

RecommendsView on HN
@carlosdp2016 · in “HTC Vive Headset Nearing 100,000 Sales”

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: [VIDEO] .

CitesView on HN
@trendia2016 · in “Virtual Forest”

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] [VIDEO]

CitesView on HN
@alfiedotwtf2024 · in “Adobe's new image rotation tool is one of the most impressive AI tools seen”

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

Strongly recommendsView on HN
@leviathant2024 · in “Adobe's new image rotation tool is one of the most impressive AI tools seen”

>SIGGRAPH from over a decade ago has entered the chat... > > [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.

CitesView on HN