Nvidia demos AI method to convert 30fps image into 480fps slow motion video
Researchers from Nvidia developed a method to use AI for the interpolation of video images. This makes it possible to convert a standard recording in for example 30fps into a slow motion video of, for example, 240 or 480fps. Check out the video below the fold, it's pretty impressive.
Researchers from NVIDIA developed a deep learning-based system that can produce high-quality slow-motion videos from a 30-frame-per-second video, outperforming various state-of-the-art methods that aim to do the same. The researchers will present their work at the annual Computer Vision and Pattern Recognition (CVPR) conference in Salt Lake City, Utah this week.
“There are many memorable moments in your life that you might want to record with a camera in slow-motion because they are hard to see clearly with your eyes: the first time a baby walks, a difficult skateboard trick, a dog catching a ball,” the researchers wrote in the research paper. “While it is possible to take 240-frame-per-second videos with a cell phone, recording everything at high frame rates is impractical, as it requires large memories and is power-intensive for mobile devices,” the team explained. With this new research, users can slow down their recordings after taking them. Using NVIDIA Tesla V100 GPUs and cuDNN-accelerated PyTorch deep learning framework the team trained their system on over 11,000 videos of everyday and sports activities shot at 240 frames-per-second. Once trained, the convolutional neural network predicted the extra frames. The team used a separate dataset to validate the accuracy of their system. The result can make videos shot at a lower frame rate look more fluid and less blurry.
“Our method can generate multiple intermediate frames that are spatially and temporally coherent,” the researchers said. “Our multi-frame approach consistently outperforms state-of-the-art single frame methods.”
To help demonstrate the research, the team took a series of clips from The Slow Mo Guys, a popular slow-motion based science and technology entertainment YouTube series created by Gavin Free, starring himself and his friend Daniel Gruchy, and made their videos even slower. The method can take everyday videos of life’s most precious moments and slow them down to look like your favorite cinematic slow-motion scenes, adding suspense, emphasis, and anticipation.
Nvidia DGX-2 Is First 2 Petaflop Deep Learning System - 03/27/2018 07:18 PM
NVIDIA today unveiled a series of important advances to its world-leading deep learning computing platform, which delivers a 10x performance boost on deep learning workloads compared with the previous...
Nvidia Doubling Up prices on GeForce GXT 2080? Tackling Some Rumors - 03/02/2018 11:29 AM
Ever since a week or 3-4, there have been massive amounts of chatter about NVIDIA Ampere (GeForce cards) and, what we assume to be, Turing (Mining / HPC Cards). You might have read and heard about it ...
Aquantia Provides Multi-Gig Networking Support for NVIDIA DRIVE Xavier & Pegasus - 01/31/2018 06:48 PM
Aquantia is announcing a new suite of products targeted at autonomous vehicle platforms – their AQcelerate product line is providing the Multi-Gig networking support for the NVIDIA DRIVE Xa...
Nvidia Delivers Xavier SoC in 2018 - 09/27/2017 08:10 AM
Nvidia's Xavier based SoC for automotive purposes will be released in 2018. Xavier is based on Volta architecture and intended for autonomous cars, drones and industrial robots. ...
Nvidia DGX-1 With Tesla V100 Spotted in GeekBench With Staggering Numbers - 09/18/2017 12:40 PM
Back in May Nvidia announced its Testla Volta V100 processor with Tensor architecture. The companies TSMC’s 12nm finfet process bakes graphics processor has 5120 shader processors activated...
Senior Member
Posts: 6575
Joined: 2012-11-10
This is legitimately really cool. I'm curious to see what some of the failed attempts look like (not to ridicule, but just because I have a fascination with how AI interprets things).
This is the kind of technology I want Nvidia to invest in, not proprietary gaming technology that screws over consumers.
Senior Member
Posts: 1787
Joined: 2013-06-04
Image quality suffers a bit, and artefacts are visible. But, looks better to me over the price of a phantom camera! Oh wait, it's Ngreedia we're talking about, it probably only runs on Titan V.
Senior Member
Posts: 6575
Joined: 2012-11-10
That awkward realization that running on a Titan V would be the cheap option. The article says it actually runs on the V100. To my knowledge, those are $10k a piece.
Senior Member
Posts: 11568
Joined: 2010-12-27
This is legitimately really cool. I'm curious to see what some of the failed attempts look like (not to ridicule, but just because I have a fascination with how AI interprets things).
This is the kind of technology I want Nvidia to invest in, not proprietary gaming technology that screws over consumers.
It's not perfect by any means but it is pretty cool how AI extrapolates information.
Image quality suffers a bit, and artefacts are visible. But, looks better to me over the price of a phantom camera! Oh wait, it's Ngreedia we're talking about, it probably only runs on Titan V.
Why are all your posts pure negativity?
Why don't you just stay out of Intel and nvidia; that's all your posts are, negative and add nothing constructive.
Title says AI.
AI requires tensor cores.
General GPUs do not have compute performance for those simulations.
Senior Member
Posts: 162
Joined: 2018-06-15
Nice idea if you can get it to work.
sadly though this is far from perfect.
But keep trying your budget is huge.
im sure in time you will crack it.
https://streamable.com/dit4h