Outer Rim Archives
Archives · 2026 · 20260214280

Application (pre-grant publication)

Video Encoding Systems and Methods

Number
20260214280
Published
2026-07-23
Filed
2026-03-19
Assignee
Disney Enterprises, Inc.
Inventors
Djelouah; Abdelaziz, Helminger; Leonhard Markus, Azevedo; Roberto Gerson de Albuquerque, Labrozzi; Scott, Schroers; Christopher Richard, Xue; Yuanyi
CPC
H04N19/503; H04N19/89; G06N3/045; G06N3/0455; G06N3/0464; G06N3/0475; G06N3/088; G06N3/09; G06N3/094
Verdict
Set aside streaming, codec
In edition
2026-W30
Source
Google Patents · FreePatentsOnline

The keeper's note

There is provided a video encoder including a processing hardware, and a system memory storing a software code.

Abstract

There is provided a video encoder including a processing hardware, and a system memory storing a software code. The processing hardware is configured to execute the software code to receive an uncompressed video content and a motion compensated video content corresponding to the uncompressed video content, transform the uncompressed video content to a first latent space representation of the uncompressed video content, transform the motion compensated video content to a second latent space representation of the uncompressed video content, determine, using the first latent space representation and the second latent space representation, a latent space residual, and generate, using the latent space residual, a compressed video content corresponding to the uncompressed video content.

Background

BACKGROUND

Video content represents the majority of total Internet traffic and is expected to increase even more as spatial resolution frame rate, and color depth of videos increase and more users adopt streaming services. Although existing codecs have achieved impressive performance, they have been engineered to the point where adding further small improvements is unlikely to meet future demands. Consequently, exploring fundamentally different ways to perform video coding may advantageously lead to a new class of video codecs with improved performance and flexibility.

For example, one advantage of using a trained machine learning (ML) model, such as a neural network (NN), in the form of a generative adversarial network (GAN) for example, to perform video compression is that it enables the ML model to infer visual details that it would otherwise be costly in terms of data transmission, to obtain. However, training ML models such as GANs is typically challenging because the training alternates between minimization and maximization steps to converge to a saddle point of the loss function. The task becomes more challenging when considering the temporal domain and the increased complexity it introduces.

Claims

21: A video encoder comprising: a processing hardware; and a system memory storing a software code; the processing hardware configured to execute the software code to: receive an uncompressed video content and a motion compensated video content corresponding to the uncompressed video content; transform the uncompressed video content to a first latent space representation of the uncompressed video content; transform the motion compensated video content to a second latent space representation of the uncompressed video content; determine, using the first latent space representation and the second latent space representation, a latent space residual; and generate, using the latent space residual, a compressed video content corresponding to the uncompressed video content. || 28: A method of video encoding comprising: receiving an uncompressed video content and a motion compensated video content corresponding to the uncompressed video content; transforming the uncompressed video content to a first latent space representation of the uncompressed video content; transforming the motion compensated video content to a second latent space representation of the uncompressed video content; determining, using the first latent space representation and the second latent space representation, a latent space residual; and generating, using the latent space residual, a compressed video content corresponding to the uncompressed video content. || 35: A computer-readable non-transitory storage medium having stored thereon a software code, which when executed by a hardware processor, performs a method comprising: receiving an uncompressed video content and a motion compensated video content corresponding to the uncompressed video content; transforming the uncompressed video content to a first latent space representation of the uncompressed video content; transforming the motion compensated video content to a second latent space representation of the uncompressed video content; determining, using the first latent space representation and the second latent space representation, a latent space residual; and generating, using the latent space residual, a compressed video content corresponding to the uncompressed video content.