slow motion footage

AI recreates missing frames to fake slo-mo footage from 30fps video

Image credit: Dreamstime

A deep-learning system that can create slow-motion scenes from standardly shot video footage has been developed by Nvidia researchers.

The system can produce high-quality slow-motion videos from a 30-frame-per-second video and the researchers claim it outperforms various state-of-the-art methods that aim to do the same. 

Given two consecutive frames, the video interpolation system generates intermediate frames to form both spatially and temporally coherent video sequences.

“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. 

“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 neural network was able to predict and insert 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.

Recent articles

Info Message

Our sites use cookies to support some functionality, and to collect anonymous user data.

Learn more about IET cookies and how to control them