- Number
- 20250106353
- Published
- 2025-03-27
- Filed
- 2024-09-19
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Zhang; Yang et al.
- CPC
- G06T7/246; H04N7/01; G06N3/045; G06V10/82; G06V20/46; H04N7/012
- Verdict
- Set aside video deinterlacing, plumbing
- Source
- Google Patents · FreePatentsOnline
Abstract
In some embodiments, a method receives a video including interlaced frames. Second fields for a second frame and the second fields for a third frame are analyzed to determine estimated second fields for the first frame in an image space. The method converts the first fields and the estimated second fields for the first frame into first features and second features, respectively, in a feature space. The estimated second features are determined for the estimated second fields for the first frame based on the first features for the first frame. Backward features from the second frame and forward features from the third frame are used to determine the estimated second features for the first frame. The method outputs a prediction for the estimated second fields for the first frame based on the estimated second features and generates a first frame with the first fields and estimated second fields.
Background
BACKGROUND
Interlaced video originated from the limitations of early television and display technologies. Interlaced video was developed as a solution to balance visual quality and technical constraints within the available bandwidth and refresh rates. Interlaced video content is captured line by line as scanlines. Within each frame, the even-numbered fields (e.g., scanlines) are captured in one frame, and the odd-numbered fields are captured in the following frame. During playback or display, the captured even and odd fields are alternately displayed on the screen. This results in two consecutive frames being combined into a single interlaced frame, where odd fields come from the first frame and even fields come from the next frame. The process happens quickly such that the human eye perceives the two fields as one continuous frame. This is called “Interlaced scanning”.
While interlacing was once a useful technique, some modern displays may require progressive video, which requires full frames. However, in the past, when using interlacing of videos, the original frames may not have been preserved. Consequently, the missing fields for frames are not available. Deinterlacing may be used to restore the missing information in legacy video content.
Claims
1. A method comprising: receiving a video including interlaced frames, wherein the interlaced frames include a first frame with first fields from original frames of the video, a second frame and a third frame with second fields from original frames of the video; analyzing the second fields for the second frame to determine first information and the second fields for the third frame to determine second information, wherein the first information and the second information are for estimated second fields for the first frame in an image space; converting the first fields, the first information, and the second information into first features, second features, and third features, respectively, in a feature space; refining the first features, the second features, and the third features in the feature space to determine refined first features, refined second features, and refined third features; outputting a prediction for the estimated second fields for the first frame based on the refined first features, refined second features, and refined third features; and using the prediction to generate a first frame with the first fields and estimated second fields. ||
15. A non-transitory computer-readable storage medium having stored thereon computer executable instructions, which when executed by a computing device, cause the computing device to be operable for: receiving a video including interlaced frames, wherein the interlaced frames include a first frame with first fields from original frames of the video, a second frame and a third frame with second fields from original frames of the video; analyzing the second fields for the second frame to determine first information and the second fields for the third frame to determine second information, wherein the first information and the second information are for estimated second fields for the first frame in an image space; converting the first fields, the first information, and the second information into first features, second features, and third features, respectively, in a feature space; refining the first features, the second features, and the third features in the feature space to determine refined first features, refined second features, and refined third features; outputting a prediction for the estimated second fields for the first frame based on the refined first features, refined second features, and refined third features; and using the prediction to generate a first frame with the first fields and estimated second fields. ||
20. An apparatus comprising: one or more computer processors; and a computer-readable storage medium comprising instructions for controlling the one or more computer processors to be operable for: receiving a video including interlaced frames, wherein the interlaced frames include a first frame with first fields from original frames of the video, a second frame and a third frame with second fields from original frames of the video; analyzing the second fields for the second frame to determine first information and the second fields for the third frame to determine second information, wherein the first information and the second information are for estimated second fields for the first frame in an image space; converting the first fields, the first information, and the second information into first features, second features, and third features, respectively, in a feature space; refining the first features, the second features, and the third features in the feature space to determine refined first features, refined second features, and refined third features; outputting a prediction for the estimated second fields for the first frame based on the refined first features, refined second features, and refined third features; and using the prediction to generate a first frame with the first fields and estimated second fields.