Generation super sampling
Frame generation super sampling may include generating an image frame embedding from a first image frame in an image stream and predicting a synthetic second image frame in the image stream using the image frame embedding of the first image in the image stream. The synthetic second image is displayed frame after the first image frame in the image stream.
1 . A method for frame generation super sampling, comprising:
generating a first image frame embedding from a first image frame in an image stream;
before generating a second image frame embedding from a second image in the image stream, predicting a synthetic image frame in the image stream using the first image frame embedding of the first image frame in the image stream;
displaying the synthetic image frame after the first image frame in the image stream; and
after displaying the synthetic image frame, displaying the second image frame in the image stream.
2 . The method of claim 1 , wherein generating the first image frame embedding comprises generating the first image frame embedding with user input information.
3 . The method of claim 2 , wherein the user input information includes one or more button presses of an input device.
4 . The method of claim 2 , wherein the user input information includes one or more movements of an input device.
5 . The method of claim 4 , wherein the input device is a mouse or trackball or joystick.
6 . The method of claim 4 , wherein the input device is an inertial measurement unit.
7 . The method of claim 1 , wherein generating the first image frame embedding comprises generating the first image frame embedding with motion vectors from the image stream.
8 . The method of claim 1 , wherein generating the first image frame embedding from the first image frame in the image stream comprises generating the first image frame embedding in conjunction with a previous image frame in the image stream.
9 . The method of claim 1 , wherein generating the first image frame embedding includes using a neural network trained with a machine learning algorithm.
10 . The method of claim 1 , wherein predicting the synthetic image frame in the image stream using the first image frame embedding includes using a neural network trained with a machine learning algorithm.
11 . The method of claim 1 , further comprising:
predicting another synthetic image frame using the first image frame embedding; and
displaying the other synthetic image frame after displaying the synthetic image frame in the image stream.
12 . The method of claim 11 , further comprising displaying a third image frame after displaying the other synthetic image frame.
13 . The method of claim 1 , comprising:
using the first and second image frames, determining motion vectors between a matching block in the first and second image frames; and
using the motion vectors, predicting a location of the matching block in a second synthetic image.
14 . A system for frame generation super sampling, comprising:
a processor;
a memory operatively coupled to the processor;
non-transitory processor executable instructions embodied in the memory, the non-transitory processor executable instructions when executed by the processor cause the processor to carry out a method for frame generation super sampling comprising:
generating a first image frame embedding from a first image frame in an image stream;
before generating a second image frame embedding from a second image in the image stream, predicting a synthetic image frame in the image stream using the first image frame embedding of the first image frame in the image stream;
displaying the synthetic image frame after the first image frame in the image stream; and
after displaying the synthetic image frame, displaying the second image frame in the image stream.
15 . The system of claim 14 , further comprising an input device,
wherein generating the first image frame embedding from the first image frame in the image stream uses user input information.
16 . The system of claim 15 , wherein the user input information includes one or more button presses of the input device.
17 . The system of claim 16 , wherein the user input information includes one or more movements of the input device.
18 . The system of claim 17 , wherein the input device is a mouse or trackball or joystick.
19 . The system of claim 17 , wherein the input device is an inertial measurement unit.
20 . A non-transitory computer readable medium having computer executable instructions embedded thereon, the computer executable instructions when executed by a computer cause the computer to implement a method for frame generation super sampling comprising:
generating a first image frame embedding from a first image frame in an image stream;
before generating a second image frame embedding from a second image in the image stream, predicting a synthetic image frame in the image stream using the first image frame embedding of the first image frame in the image stream;
displaying the synthetic image frame after the first image frame in the image stream; and
after displaying the synthetic image frame, displaying the second image frame in the image stream.