viralamo

Menu
  • Technology
  • Science
  • Money
  • Culturs
  • Trending
  • Video

Subscribe To Our Website To Receive The Last Stories

Join Us Now For Free
Home
Technology
Google uses crowdsourced photos to recreate landmarks in 3D for AR/VR
Technology

Google uses crowdsourced photos to recreate landmarks in 3D for AR/VR

12/08/2020

Historically, human artists have been challenged to recreate real-world locations as 3D models, particularly when applications call for photorealistic accuracy. But Google researchers have come up with an alternative that could simultaneously automate the 3D modeling process and improve its results, using a neural network and crowdsourced photos of a location to convincingly replicate landmarks in 3D.

The idea behind neural radiance fields (NeRF) is to extract 3D depth data from 2D images by determining where light rays terminate, a sophisticated technique that alone can create plausible textured 3D models of landmarks. Google’s NeRF in the Wild (NeRF-W) system goes further in several ways. First, it uses “in-the-wild photo collections” as inputs, expanding a computer’s ability to see landmarks from multiple angles. Next, it evaluates the images to find structures, separating out photographic and environmental variations such as image exposure, scene lighting, post-processing, and weather conditions, as well as shot-to-shot object differences such as people who might be in one image but not another. Then it recreates scenes as mixes of static elements — structure geometry and textures — with transient ones that provide volumetric radiance.

As a result, NeRF-W’s 3D models of landmarks can be smoothly viewed from multiple angles without looking jittery or artifacted, while the lighting system uses the detected variations to provide radiance guidance for scene lighting and shadowing. NeRF-W can also treat image-to-image object differences as an uncertainty field, either eliminating or de-emphasizing them, whereas the standard NeRF system allows those differences to appear as cloud-like occluding artifacts, because it doesn’t separate them from structures during image ingestion.

Google’s video comparison of standard NeRF results with NeRF-W suggests that the new neural system can so convincingly recreate landmarks in 3D that virtual reality and augmented reality device users will be able to experience complex architecture as it actually looks, including time-of-day and weather variations. It’s also offered as an improvement on a similar alternative disclosed last near, Neural Rerendering in the Wild, by doing a better job of separating 3D structures from lighting, and looking more temporally smooth as objects are viewed from different angles.

It’s worth noting that Google certainly isn’t the only company researching ways to use photos as input for 3D modeling; Intel researchers, for instance, are advancing their own work in generating synthesized versions of real world locations, using multiple photographs plus a recurrent encoder-decoder network to interpolate uncaptured angles. While Intel’s system appears to outperform numerous alternatives — including standard NeRF — on pixel-level sharpness and temporal smoothness, it doesn’t appear to offer the variable lighting capabilities of NeRF-W, or have the same focus on using randomly sourced photos to recreate real-world locations.

Google’s NeRF-W is discussed in detail in this paper, which arrives just ahead of the August 23 European Conference on Computer Vision 2020. A video showing its performance with landmarks such as Germany’s Brandenburg Gate and Rome’s Trevi Fountain is available here.

Source link

Share
Tweet
Pinterest
Linkedin
Stumble
Google+
Email
Prev Article
Next Article

Related Articles

Tray.io raises $50 million to automate repetitive business processes
Automating monotonous records management, customer relationship management, IT, and human …

Tray.io raises $50 million to automate repetitive business processes

How to raise money – it’s a journey not an event
Every year I teach classrooms full of students who leave …

How to raise money – it’s a journey not an event

Leave a Reply Cancel reply

Find us on Facebook

Related Posts

  • Supply-chain attack hits RubyGems repository with 725 malicious packages
    Supply-chain attack hits RubyGems repository with 725 …
    17/04/2020
  • Beat Saber is now an Oculus studio after Facebook acquisition
    Energica CEO plots her Italian EV company’s …
    09/04/2020
  • Intel launches Iris Xe Max graphics chip with three laptop makers
    Intel launches Iris Xe Max graphics chip …
    31/10/2020
  • Facebook’s Hanabi-playing AI achieves state-of-the-art results
    Facebook research reveals AI tools for improving …
    16/06/2020
  • Fast & Furious: Crossroads lives video games a quarter-mile at a time
    In Los Angeles, the Women’s March embraces …
    19/01/2020

Popular Posts

  • Hackers tied to Russia’s GRU targeted the US grid for years
    Hackers tied to Russia’s GRU targeted the …
    27/02/2021 0
  • Cox slows Internet speeds in entire neighborhoods to punish any heavy users
    Cable ISP warns “excessive” uploaders, says network …
    29/01/2021 0
  • 10 Best Supernatural Occurrences Caught On Camera …
    30/01/2021 0
  • Top 10 Most Uncomfortable Addictions – Listverse
    30/01/2021 0
  • Top 10 Scariest Government Experiments – Listverse
    01/02/2021 0

viralamo

Pages

  • Contact Us
  • Privacy Policy
Copyright © 2021 viralamo
Theme by MyThemeShop.com

Ad Blocker Detected

Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker.

Refresh