Research team from NVIDIA is presenting new deep learning based system able to create good-looking fake slow motion in the post production. They claim their software can generate the in-between frames in a more convincing way than the existing solution. Example of the Resulting Slow Motion Footage. Source: NVIDIA The idea of creating “fake” slow motion in post production is not new. Computers can insert artificially created frames in between existing frames and therefore increase the resulting framerate of the footage. The existing solution from RE:Vision Effects called Twixtor however gives nice results only under perfect circumstances. Like for example a simple moving object on an even background. As soon as there is a complex very fast movement and/or broken background included, the resulting frames are not convincing and objects are falling apart. Researchers from NVIDIA developed a new system based on deep learning which can produce better results. They aim to present their work at the annual Computer Vision and Pattern Recognition (CVPR) conference on June 21st in Salt Lake City, Utah. The team achieved the results by using NVIDIA Tesla V100 GPUs and cuDNN-accelerated deep learning framework. Scientists trained the system on over 11,000 videos of everyday and sports activities shot natively at 240 frames-per-second. Once trained, the convolutional neural network was able to predict the extra frames with a better accuracy. NVIDIA team claims their method can generate multiple intermediate frames that are spatially and temporally coherent. To demonstrate the capabilities of the new system the research team published a short...
Published By: CineD - Wednesday, 20 June, 2018