Hacker News Reader

What's new about this? That it's faster? People have been reconstructing 3D images from multiple photos for over a decade. The experimental work today is constructing a 3D image from a single photo, using a neural net to fill in a reasonable model of the stuff you can't see.

View on HN

Five years ago, I've used common software to do this. I had to take hundreds of pictures of a scene, getting as many angles and details possible. Then when you pass it to the computer. Stitching it all together took well beyond 24 hours.

Now that I had a 3d model of the scene, I had to spend countless hours cleaning it up to make sure it was useable. Maybe in the last 5 years, things have improved.

But this demo used 4 pictures. And apparently, it rendered the final image in seconds. That's what's new.

If I understand it correctly it didn't make a 3d model, though. So you can't extract and reuse the result. Only move around in it and it creates an image for that viewpoint. But no meshes or textures.

Did it really use only 4 pictures? Do you have a source? https://news.ycombinator.com/item?id=30810885

it's not just faster, it's extremely faster. They're achieving results that are better than SOTA in a fraction of the time. Wildly impressive work.

This type of thing looks like the future of Meta or even Zoom to me.

Reply on news.ycombinator.com