Apparatus and methods for image encoding using spatially weighted encoding quality parameters

Patent metadata

Field	Value
Publication number	US-12477231-B2
Application number	US-202318137021-A
Country	US
Kind code	B2
Filing date	Apr 20, 2023
Priority date	Jun 17, 2016
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Visual content that includes spatial portions is obtained. A determination is made that one of the spatial portions includes a face. Based on the determination, encoding quality parameters for the one of the spatial portions is identified. The encoding quality parameters are obtained by combining a first distortion model related to the obtaining the visual content with a second model that emphasizes the one of the spatial portions The visual content is encoded. The encoding quality parameters are stored, in association with but separate from, the one of the spatial portions. After decoding, the one of the spatial portions are rendered based on the encoding quality parameters. The encoding quality parameters are obtained by combining a first distortion model related to the obtaining the visual content with a second model that emphasizes the one of the spatial portions.

First claim

What is claimed is:

1 . A method, comprising:
obtaining visual content, the visual content comprising spatial portions; determining that one of the spatial portions includes a face; identifying, based on the determination, encoding quality parameters for the one of the spatial portions, wherein the encoding quality parameters are obtained by combining a first distortion model related to the obtaining the visual content with a second model that provides higher encoding quality for the one of the spatial portions; encoding the visual content; storing, in association with but separate from the one of the spatial portions, the encoding quality parameters; and rendering, after decoding, the one of the spatial portions based on the encoding quality parameters.

2 . The method of claim 1 , wherein the visual content is captured using a non- uniform image capture device, and wherein the visual content is one of a binocular image content, a spherical image content, or a panoramic image content.

3 . The method of claim 1 , wherein the second model provides the higher encoding quality for the one of the spatial portions by concentrating processing resources toward high encoding quality for the one of the spatial portions.

4 . The method of claim 1 , wherein the encoding quality parameters are identified based on a distortion model associated with a lens type used to obtain the visual content.

5 . The method of claim 4 , wherein the distortion model is an equirectangular projection that is such that a maximum quality equirectangular projection is at an equator of the visual content.

6 . The method of claim 1 , wherein the determination that the one of the spatial portions includes a face is based on user input.

7 . The method of claim 6 , wherein the user input is obtained after encoding the visual content.

8 . The method of claim 1 , wherein the determination that the one of the spatial portions includes a face is made by an encoding process that encodes the visual content.

9 . A device, comprising:
a memory; and a processor, the processor configured to execute instructions stored in the memory to:
obtain encoded visual content from visual content, the encoded visual content comprising an encoded spatial portion, wherein the encoded visual content is obtained from an encoding process by instructions to:
determine that a spatial portion corresponding to the encoded spatial portion includes a face;
encode the visual content using the encoding process; and
store an indication of the spatial portion that includes the face;

identify, based on the indication, encoding quality parameters for the spatial portion; and
render, after decoding of at least the encoded spatial portion, the spatial portion based on the encoding quality parameters.

10 . The device of claim 9 , wherein the encoding quality parameters are further identified in response to a request to render the spatial portion.

11 . The device of claim 9 ,
wherein the encoded spatial portion is a first encoded spatial portion, the spatial portion is a first spatial portion, and the encoding quality parameters are first encoding quality parameters, wherein the encoded visual content includes a second encoded spatial portion of a second spatial portion, and wherein the processor is further configured to identify, for the second spatial portion, second encoding quality parameters that are based on a non-uniform capture of the visual content.

12 . The device of claim 11 , wherein the second encoding quality parameters are dependent on a location of the second spatial portion in the visual content.

13 . The device of claim 11 , wherein the second encoding quality parameters are identified based on a mathematical relationship.

14 . The device of claim 11 , wherein the second encoding quality parameters are identified based on a relationship of spatial portions to respective encoding quality parameters.

15 . A non-transitory memory, comprising executable instructions that, when executed by a processor, facilitate performance of operations, the operations comprising operations to:
obtain visual content, the visual content comprising spatial portions; identify a face in a subset of the spatial portions; and encode at least some of the spatial portions of the visual content based on spatially weighted encoding quality parameters, wherein the spatially weighted encoding quality parameters are obtained by combining a first distortion model related to the obtained visual content with a second model that provides higher encoding quality for the subset of the spatial portions.

16 . The non-transitory memory of claim 15 , wherein the visual content is captured using a non-uniform image capture, and wherein the visual content is one of a binocular image content, a spherical image content, or a panoramic image content.

17 . The non-transitory memory of claim 15 , wherein the second model provides the higher encoding quality for the subset of the spatial portions by concentrating processing resources toward high encoding quality for the subset of the spatial portions.

18 . The non-transitory memory of claim 15 , wherein the first distortion model is based on a lens type used to obtain the visual content.

19 . The non-transitory memory of claim 15 , wherein the first distortion model is an equirectangular projection that is such that a maximum quality equirectangular projection is at an equator of the visual content.

20 . The non-transitory memory of claim 15 , wherein the face is identified by an encoding process.

Assignees

• Gopro Inc

Inventors

• Adsumilli Balineedu Chowdary
• Abbas Adeel
• Chawla Sumit

Classifications

• H04N13/344

  with head-mounted left-right displays · CPC title

• H04N13/178

  Metadata, e.g. disparity information · CPC title

• H04N13/296

  Synchronisation thereof; Control thereof · CPC title

• H04N13/243

  using three or more two-dimensional [2D] image sensors · CPC title

• H04N19/57

  Motion estimation characterised by a search window with variable size or shape · CPC title