Abstract:
An apparatus to facilitate video motion smoothing is disclosed. The apparatus comprises one or more processors including a graphics processor, the one or more processors including circuitry configured to receive a video stream, decode the video stream to generate a motion vector map and a plurality of video image frames, analyze the motion vector map to detect a plurality of candidate frames, wherein the plurality of candidate frames comprise a period of discontinuous motion in the plurality of video image frames and the plurality of candidate frames are determined based on a classification generated via a convolutional neural network (CNN), generate, via a generative adversarial network (GAN), one or more synthetic frames based on the plurality of candidate frames, insert the one or more synthetic frames between the plurality of candidate frames to generate up-sampled video frames and transmit the up-sampled video frames for display.
Abstract:
In at least one embodiment described herein, an apparatus is provided that can include means for communicating a latency tolerance value for a device connected to a platform from a software latency register if a software latency tolerance register mode is active. The apparatus may also include means for communicating the latency tolerance value from a hardware latency register if a host controller is active. The latency tolerance value can be sent to a power management controller. More specific examples can include means for communicating a latency tolerance value from the software latency register if the software latency tolerance register mode is not active and the host controller is not active. The apparatus can also include means for mapping a resource space in the software latency register for the device using a BIOS/platform driver. The mapping can be achieved using an advanced configuration and power interface device description.
Abstract:
An apparatus to facilitate video motion smoothing is disclosed. The apparatus comprises one or more processors including a graphics processor, the one or more processors including circuitry configured to receive a video stream, decode the video stream to generate a motion vector map and a plurality of video image frames, analyze the motion vector map to detect a plurality of candidate frames, wherein the plurality of candidate frames comprise a period of discontinuous motion in the plurality of video image frames and the plurality of candidate frames are determined based on a classification generated via a convolutional neural network (CNN), generate, via a generative adversarial network (GAN), one or more synthetic frames based on the plurality of candidate frames, insert the one or more synthetic frames between the plurality of candidate frames to generate up-sampled video frames and transmit the up-sampled video frames for display.