The new system from NVIDIA seems to deliver better results than the existing solution although it is yet to be seen on more examples. The demonstrated clips look quite astounding.
In the next part of the video, NVIDIA took some footage from the youtube channel The Slow Mo Guys which was already filmed in high framerate and slowed it down even more. Obviously, the new deep learning based system is not perfect yet. Another artifact can be visible on the dancer’s hair. Later in the video, however, we can see some artifacts in the clip with a hockey player (the movement of his glove and skates).
#Twixtor review software#
The NVIDIA software did a pretty good job calculating the additional 210 frames for every second (7 artificial frames between two real frames). The first clip of a moving car looks quite convincing in my opinion. The demonstration video initially shows results of slowing down a 30fps footage down to 240fps. To demonstrate the capabilities of the new system the research team published a short video on YouTube. NVIDIA team claims their method can generate multiple intermediate frames that are spatially and temporally coherent. Once trained, the convolutional neural network was able to predict the extra frames with a better accuracy. Scientists trained the system on over 11,000 videos of everyday and sports activities shot natively at 240 frames-per-second. The team achieved the results by using NVIDIA Tesla V100 GPUs and cuDNN-accelerated deep learning framework. They aim to present their work at the upcoming annual Computer Vision and Pattern Recognition (CVPR) conference on June 21st in Salt Lake City, Utah. Researchers from NVIDIA developed a new system based on deep learning which can produce better results. As soon as there is a complex very fast movement and/or uneven background included, the resulting frames are not convincing and objects are falling apart. For example, on a simple moving object on an even background. However, the existing market-leading solution is a special piece of software from RE:Vision Effects called Twixtor– which however gives nice results only under perfect circumstances.
#Twixtor review pro#
Normal NLEs do this through simple frame blending (whereas Final Cut Pro X seems to do it better than Premiere Pro CC still). Computers can generate frames artifically in between existing frames and therefore increase the resulting framerate of the footage. The idea of creating “fake” slow motion in post production is not new. Example of the Resulting Slow Motion Footage.
0 kommentar(er)
