Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 18 submissions in the queue.
posted by janrinok on Monday March 28 2022, @04:32AM   Printer-friendly

Nvidia shows off AI model that turns a few dozen snapshots into a 3D-rendered scene

Nvidia's latest AI demo is pretty impressive: a tool that quickly turns a "few dozen" 2D snapshots into a 3D-rendered scene. In the video below you can see the method in action, with a model dressed like Andy Warhol holding an old-fashioned Polaroid camera. (Don't overthink the Warhol connection: it's just a bit of PR scene dressing.)

The tool is called Instant NeRF, referring to "neural radiance fields" — a technique developed by researchers from UC Berkeley, Google Research, and UC San Diego in 2020. If you want a detailed explainer of neural radiance fields, you can read one here, but in short, the method maps the color and light intensity of different 2D shots, then generates data to connect these images from different vantage points and render a finished 3D scene. In addition to images, the system requires data about the position of the camera.

Researchers have been improving this sort of 2D-to-3D model for a couple of years now, adding more detail to finished renders and increasing rendering speed. Nvidia says its new Instant NeRF model is one of the fastest yet developed and reduces rendering time from a few minutes to a process that is finished "almost instantly."

Also at Tom's Hardware and PetaPixel.

Previously: Breakthrough AI Technique Enables Real-Time Rendering of Scenes in 3D From 2D Images


Original Submission

Related Stories

Breakthrough AI Technique Enables Real-Time Rendering of Scenes in 3D From 2D Images 6 comments

Breakthrough AI Technique Enables Real-Time Rendering of Scenes in 3D From 2D Images:

Humans are pretty good at looking at a single two-dimensional image and understanding the full three-dimensional scene that it captures. Artificial intelligence agents are not.

Yet a machine that needs to interact with objects in the world — like a robot designed to harvest crops or assist with surgery — must be able to infer properties about a 3D scene from observations of the 2D images it's trained on.

While scientists have had success using neural networks to infer representations of 3D scenes from images, these machine learning methods aren't fast enough to make them feasible for many real-world applications.

A new technique demonstrated by researchers at MIT and elsewhere is able to represent 3D scenes from images about 15,000 times faster than some existing models.

The method represents a scene as a 360-degree light field, which is a function that describes all the light rays in a 3D space, flowing through every point and in every direction. The light field is encoded into a neural network, which enables faster rendering of the underlying 3D scene from an image.

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 2) by Freeman on Monday March 28 2022, @01:43PM (1 child)

    by Freeman (732) on Monday March 28 2022, @01:43PM (#1232928) Journal

    Not sure how useful it is, but it's definitely interesting. Wonder, if it could be used to help speed up game development? You need to recreate New York City? Here's a few polaroids from the 1980s. Poof, instant New York City 80s theme.

    --
    Joshua 1:9 "Be strong and of a good courage; be not afraid, neither be thou dismayed: for the Lord thy God is with thee"
    • (Score: 0) by Anonymous Coward on Monday March 28 2022, @02:35PM

      by Anonymous Coward on Monday March 28 2022, @02:35PM (#1232943)

      That sounds like more of a machine learning algorithm problem, assuming you are talking about creating stuff out of the scene of your original polaroids.

  • (Score: 0) by Anonymous Coward on Monday March 28 2022, @01:48PM

    by Anonymous Coward on Monday March 28 2022, @01:48PM (#1232929)

    Hmmm.

  • (Score: 1, Informative) by Anonymous Coward on Monday March 28 2022, @07:35PM

    by Anonymous Coward on Monday March 28 2022, @07:35PM (#1233019)

    This is a case where I can save my snark and let you just read from their Github site [github.com] yourself:

    What is a NeRF?
    A neural radiance field is a simple fully connected network (weights are ~5MB) trained to reproduce input views of a single scene using a rendering loss. The network directly maps from spatial location and viewing direction (5D input) to color and opacity (4D output), acting as the "volume" so we can use volume rendering to differentiably render new views.

    Optimizing a NeRF takes between a few hours and a day or two (depending on resolution) and only requires a single GPU. Rendering an image from an optimized NeRF takes somewhere between less than a second and ~30 seconds, again depending on resolution.

    So you can feed it your image set and it will take you two days to get an optimized NeRF, but once you have that, it will make a picture "almost instantly."

(1)