Systems and methods for image compression at multiple, different bitrates

Number: 11335034
Published: 2022-05-17
Filed: 2019-01-16
Assignee: Disney Enterprises, Inc.
Inventors: Schroers; Christopher, Doggett; Erika, Mandt; Stephan Marcel, McPhillen; Jared, Labrozzi; Scott, Weber; Romann, Bamert; Mauro
CPC: H04N19/50; H04N19/147; H04N19/124; G06T9/20
Verdict: Set aside image/video compression codec
Source: Google Patents · FreePatentsOnline

Abstract

Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

Background

TECHNICAL FIELD (1) The present disclosure relates generally to image compression. BRIEF SUMMARY OF THE DISCLOSURE (2) Embodiments of the disclosure are directed to systems and methods for predicting a target set of pixels. (3) In one embodiment, a computer-implemented method may be implemented in a computer system that includes non-transient electronic storage and one or more physical computer processors. The computer-implemented method may include obtaining, from the non-transient electronic storage, target content that includes the target set of pixels to be predicted. The computer-implemented method may include convolving, with the one or more physical computer processors, the target set of pixels to generate an estimated set of pixels. The computer-implemented method may include matching, with the one or more physical computer processors, a second set of pixels in the target content to the target set of pixels. The second set of pixels is within a distance from the target set of pixels. The computer-implemented method may include refining, with the one or more physical computer processors, the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content. (4) In embodiments, the computer-implemented method may further include generating, with the one or more physical computer processors, a residual between the refined set of pixels and the target set of pixels. (5) In embodiments, refining the estimated set of pixels may i

Claims

1. A computer-implemented method for encoding target content, the method being implemented in a computer system that comprises a non-transient electronic storage and one or more physical computer processors, comprising: obtaining, from the non-transient electronic storage, target content and a corresponding quantization step size; obtaining, from the non-transient electronic storage, a trained compression model, the trained compression model conditioned by training an initial compression model using training data, wherein the training data comprises (i) a set of training content, (ii) for each training content included in the set of training content, a plurality of quantization step sizes for quantizing the training content, and (iii) for each training content included in the set of training content, a plurality of reconstruction losses based on differences between the training content and a corresponding quantized training content that was quantized using a given quantization step size included in the plurality of quantization step sizes; and applying, with the one or more physical computer processors, the trained compression model to the target content to generate compressed target content. || 9. A computer-implemented method for training a compression model that improves quantization of target content, the method being implemented in a computer system, the computer system including one or more physical computer processors and a non-transitory electronic storage, comprising: obtaining, from the non-transient electronic storage, training data, the training data comprising (i) a set of training content, (ii) for each training content included in the set of training content, a plurality of quantization step sizes for quantizing the training content, and (iii) for each training content included in the set of training content, a plurality of reconstruction losses based on differences between the training content and a corresponding quantized training content that was quantized using a given quantization step size included in the plurality of quantization step sizes; obtaining, from the non-transient electronic storage, an initial compression model; generating a trained compression model by training, on the one or more physical computer processors using the training data, the initial compression model; and storing, in the non-transient electronic storage, the trained compression model.