Google researchers have unveiled detailed 3D scenes of famous landmarks around the world. They
On the project's GitHub page, researchersshared 3D scenes of the Brandenburg Gate in Berlin, the Basilica of the Sacre Coeur in Paris and the Trevi Fountain in Rome. Machine learning has created detailed 3D rendering from this material, in which you can move the view, and the external scene changes with lighting effects.
Our paper, “NeRF in the Wild”, is out! NeRF-W is a method for reconstructing 3D scenes from internet photography. We apply it to the kinds of photos you might take on vacation: tourists, poor lighting, filters, and all. https://t.co/lawLB4eEup (1 / n) pic.twitter.com/UuvUm4eVzm
— Daniel Duckworth (@duck) August 6, 2020
The researchers explained that their algorithm canface difficulties when using images with "unusual parameters". Photos are not processed correctly in poor light, incorrect exposure, or post-processing. In addition, images from the Internet often contain moving objects - for example, people or cars. They can also interfere with the algorithm.
“Two photographers can stand in one place andtake a snapshot of the same sight, but the algorithm will process one frame correctly, and spoil the second. We need to refine the AI to make it work correctly, ”the researchers noted.
The resulting model may contain glitches or other errors. Researchers are developing special extensions that soften the processing by AI, which leads to better results.
See also:
- The last ice shelf in Canada collapsed into the ocean. He lost 40% in two days
- See what Hubble's successor can see in space. Webb telescope overview
- Russia has opened flights with a number of countries. How safe is it to fly there?