Samsung patents video smoothing method using neural networks
Samsung has been granted a patent for a method to train neural networks that create smooth, intermediate video frames. The system compares the visual features of generated frames with real ones to adjust the model's settings, reducing the difference between them.
In the filing’s own words
An interpolation model learning method, a non-transitory computer-readable storage medium storing instructions allowing the method to be performed, and a device for learning an interpolation frame generating module are provided. The interpolation model learning method may include extracting, by using a neural network model, a temporal-spatial feature of each of a frame group including an interpolation frame generated by an interpolation model based on a neural network and a frame group including a ground truth (GT) frame corresponding to an interpolation frame and changing a weight and/or a bias of a neural network of an interpolation model to decrease a difference between temporal-spatial features.
What exactly they claim (claim 1)
1. An interpolation model learning method comprising: extracting, from a video including a plurality of continuous frames, a first ground truth (GT) frame and a plurality of frames; generating a first interpolation frame based on the plurality of frames using an interpolation model; using a first feature extraction model to extract a first temporal-spatial feature of a first frame group including at least three frames including the first GT frame; using the first feature extraction model to extract a second temporal-spatial feature of a second frame group including at least three frames including the first interpolation frame, based on the first feature extraction model; and training the interpolation model, based on the first temporal-spatial feature and the second temporal-spatial feature, wherein the training of the interpolation model comprises determining temporal-spatial loss information based on a difference between the first temporal-spatial feature and the second temporal-spatial feature, and adjusting at least one operation parameter of the interpolation model to decrease the temporal-spatial loss information.
Facts
- Company
- Samsung (Samsung Electronics Co., Ltd.)
- Official title
- Interpolation model learning method and device for learning interpolation frame generating module
- Patent number
- US12749300B2
- Application number
- 18543506
- Filed
- Dec 18, 2023
- Granted
- Sep 29, 2026
- Inventors
- 3
- Claims
- 19
Classified under
G06V 10/82 Physics & computingG06V 10/7715 Physics & computingG06V 20/46 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.