Systems and methods for generating dynamic virtual representations of an object or event
US-2024420395-A1 · Dec 19, 2024 · US
US9311901B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9311901-B2 |
| Application number | US-201414317492-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jun 27, 2014 |
| Priority date | Jun 28, 2013 |
| Publication date | Apr 12, 2016 |
| Grant date | Apr 12, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method of producing an image with a blurred background ( 151 ) from an initial image ( 111 ) and a depth map ( 112 ) identifying a foreground region ( 236 ) and a background region ( 237 ) of the image, said method comprising determining ( 670 ) an edge visibility measure ( 671 ) for one edge ( 231 ) in the depth map ( 112 ) by comparing ( 820 ) a pixel value ( 233 ) in the foreground with a pixel value ( 234 ) in the background, said edge visibility measure ( 671 ) distinguishing between the foreground ( 236 ) and the background ( 237 ); applying ( 680 ) a spatially variable blur to the depth map ( 112 ) to produce a compositing matte ( 681 ), dependent on the edge visibility measure ( 671 ); applying ( 530 ) a blur to the background region ( 521 ) of the depth map ( 112 ); and compositing ( 150 ) the blurred background image data ( 531 ) with the initial image ( 111 ) to produce the rendered image with the blurred background ( 151 ).
Opening claim text (preview).
The invention claimed is: 1. A method of producing a rendered image with a blurred background from an initial image and a depth map of the image, said depth map identifying at least one foreground region and at least one background region of the image, said method comprising the steps of: determining an edge visibility measure for at least one edge in the depth map by comparing a parameter value associated with a pixel in the foreground region near the edge with a parameter value associated with another pixel in the background region near the edge; applying a spatially variable blur to the depth map to produce a compositing matte, wherein a size of a blur kernel used to form the spatially variable blur is dependent on the determined edge visibility measure; applying a blur to image data in at least one background region of the depth map to form normalized blurred background image data; and compositing the blurred background image data with the initial image in a weighted average defined by the compositing matte to produce the rendered image with the blurred background. 2. A method according to claim 1 , wherein the comparing step compares respective colours or textures of the respective pixels in the foreground region and the background region. 3. A method according to claim 1 , wherein the comparing step compares averages of colour values or texture values of respective pluralities of pixels in the foreground region and the background region. 4. A method according to claim 1 , wherein a spatial extent of the blurred background image data in the compositing matte is limited according to a size of a blur kernel. 5. A method according to claim 1 , wherein the spatially variable blur is applied using a Gaussian filter. 6. An apparatus for producing a rendered image with a blurred background from an initial image and a depth map of the image, said depth map identifying at least one foreground region and at least one background region of the image, said apparatus comprising: a processor; and a memory storing a non-transitory computer executable program for directing the processor to perform a method comprising the steps of: determining an edge visibility measure for at least one edge in the depth map by comparing a parameter value associated with a pixel in the foreground region near the edge with a parameter value associated with another pixel in the background region near the edge; applying a spatially variable blur to the depth map to produce a compositing matte, wherein a size of a blur kernel used to form the spatially variable blur is dependent on the determined edge visibility measure; applying a blur to image data in at least one background region of the depth map to form normalized blurred background image data; and compositing the blurred background image data with the initial image in a weighted average defined by the compositing matte to produce the rendered image with the blurred background. 7. A computer readable non-transitory storage medium storing a computer executable program for directing a processor to execute a method of producing a rendered image with a blurred background from an initial image and a depth map of the image, said depth map identifying at least one foreground region and at least one background region of the image, said method comprising the steps of: determining an edge visibility measure for at least one edge in the depth map by comparing a parameter value associated with a pixel in the foreground region near the edge with a parameter value associated with another pixel in the background region near the edge; applying a spatially variable blur to the depth map to produce a compositing matte, wherein a size of a blur kernel used to form the spatially variable blur is dependent on the determined edge visibility measure; applying a blur to image data in at least one background region of the depth map to form normalized blurred background image data; and compositing the blurred background image data with the initial image in a weighted average defined by the compositing matte to produce the rendered image with the blurred background.
Related publications grouped by family.
Answers are generated from the same data shown on this page.