Ovimeister

This is true, however there are real world limitations. Some reconstruction projects for real cities have taken tens, if not hundreds of hours, and this is due to real world limitations with gpu. We are still not in that level with hardware. My point is that, if something like this wants to be pushed, we have to start somewhere don't we? I say, pick and old game you really like. Old too to avoid legalities. Bring the community together to take screenshots of everything randomly, have 2-3 guys that know their shit stitch and clean, and make meshes public. Then have people explore those worlds. BAM Public interest rises, many more projects advance trying to automate this. Edit: i believe i am failing at making a point clear so here we go. Making software to extract 3d data from games using sfm (structure from motion), is NOT a commercially viable option, at least from a AAA perspective. I don't want to look as if I am shilling my shit, but it is an example. I made an online application for sfm, which is supposed to let agricultural sectors with less resources analyze crops with just their cellphone. Analize 3d reconstructions from plants, with a toolset for morphological analysis. It was a bitch to get initial funds, and we barely were able to get a webapp going. I then opened a go fund me here, with no real success: https://gogetfunding.com/plarepi-localization/ Sure, we are only looking to localize and at best, add AI algoritms, the product is already finished... but we are still from a small country and little budget. Getting users in our country has been hard. Reality is, empowering people with tools is a risky venture for it requires as much effort educating people as it does selling said tools. It becomes niche as hell. It may be because agriculture isn't innovative on its own, it may be our country, and also that we are huge nerds with no social pull... but it doesn't take from the fact that a AAA companies aren't gonna take this risk. This is why i say that something like "the dream software" must be financed by the fans, for the fans. I don't see it happening otherwise. Even things like testing, must start with people's help. Sure, i can make a gofundme project, but, we aren't gonna achieve shit without LOTS of support. Oh, and those wondering, it should be financed, but the final product MUST be open source.

Yo ross, this video really got to me and I simply have to comment. What i am truly interested is, are you REALLY interested in helping this kind of project going? I write as a work with photogrametry, I used to be a researcher that worked in plant phenotyping and used technology like the ones that several people already commented in this thread. (WAS as bad economy left me jobless, but moved to create a business for 3d reconstructions from plants for farmers using cellphone and drone images) In reality, just free software from more than 7 years ago can be used to extract 3d data from worlds and create files that can be read by any engine. What occurs is that in practice, you dont need video, you would need thousands of images taken in specific automated manners, and then you could clean results manually, or use trainers for machine learning. Sky is the limit here. What i think is a collaborative effort to extract data, like is normally done in cultural heritage, from which things like rome have been preserved in 3d thanks to images from tourists online. We could call it, gaming heritage. However for a project of this magnitude, several points must be met: First, scratch the idea of software for extracting data. Also, the rest of the dream engine is way too far fetched. Focus on getting said data in the first place as a collaborative effort. Call on people to take images of games, upload them into a massive file-sharing service, and have a group of people convert those into 3d meshes. Share the results. I'm skipping TONS of technical details As it is transformative work is shouldn't be illegal (im no lawyer, however) Those results should be easily accessible for plenty of viewers, so people can explore said worlds. You said that you cannot do much because you are out of your league, this is false. You can make the call to make people try to collaborate on this, kickstart it somehow. I would really love to even explain the basics behind some of what structure-from-motion is, so let me know.