Google, UC Merced and Shanghai Jiao Tong University researchers have developed DAIN, a depth-aware video frame interpolation algorithm, powered by neural networks, capable of seamlessly generating slow-motion videos from existing content without adding excessive noise or unwanted artifacts. It functions by generating new frames and slotting them between the original frames, increasing the video’s FPS for ultra smooth, depending on the number of generated frames, content. Read more for two videos and additional information.
Simply put, DAIN can perform motion interpolation to boost frames-per-second up to 480fps without the artifacts introduced by other methods, thus resulting in content visually identical to the source footage, but with the smoothness of increasing the frames-per-second to 60fps.
- System: Intel Core i5-9400F 2.9 GHz 6-Core: Intel B360 Chipset | 8GB DDR4 | 240GB SSD | 1TB HDD | Genuine Windows 10 Home 64-bit
- Graphics: NVIDIA GeForce GTX 1660 6GB Video Card | 1x HDMI | 1x DisplayPort
- Connectivity: 6 x USB 3.1 | 2 x USB 2.0| 1x RJ-45 Network Ethernet 10/100/1000 | 802.11AC Wi-Fi | Audio: 7.1 Channel | Keyboard and mouse
Among those important metrics for video quality, the most important one is the temporal resolution measured in frame-per-second or fps for short. Higher-frame-rate videos bring about more immersive visual experience to users so that the reality of the captured content is perceived. Therefore, the demand to improve the low-frame-rate videos, particularly the 12fps old films, 5~12fps animations, pixel-arts and stop motions, 25~30 fps movies, 30fps video games, becomes more and more urgent,” said the researchers.