METHODS AND APPARATUS RENDERING IMAGES USING POINT CLOUDS REPRESENTING ONE OR MORE OBJECTS
A background image is also generated, e.g., by filling portions of a captured image where a foreground object was extracted and communicated to the playback device, Foreground objects are identified and point cloud representations of the foreground objects are generated and communicated to a playback device so that they can be used in generating images including the background which is communicated separately. In the case of a point cloud representation a number of points in an environment, e.g., 3D space, are communicated to the playback device along with color information. Thus in some embodiments a foreground object is represented as a set of points with corresponding color information on a per point basis. Foreground object information is communicated and processed in some embodiments at a different rate, e.g., faster rate, then the background textures.
1 . A method comprising:
capturing image data of an environment;
detecting, in the image data, a first portion of the image data comprising an object which moves in the environment, and a second portion of the image data;
obtaining a first geometric representation of the object;
communicating, to a playback device, the representation of the object without the second portion of the image data, wherein the first geometric representation of the object is configured to be rendered over a representation of the second portion of the image data.
2 . The method of claim 1 , wherein the representation of the second portion of the image data comprises a second geometric representation.
3 . The method of claim 2 , wherein the first geometric representation comprises one or more different data types than the second geometric representation.
4 . The method of claim 1 , wherein the representation of the second portion of the image data is generated from a plurality of images captured at different times.
5 . The method of claim 4 , wherein generating the representation of the second portion of the image data comprises:
identifying the object in a first image captured at a first time; and
replacing the object in the first image with image content from a stable portion of a second image captured at a second time.
6 . The method of claim 1 , further comprising:
generating an updated representation of the object, wherein the updated representation is indicative of change in location of the object.
7 . The method of claim 1 , wherein the first geometric representation of the object comprises depth data.
8 . A non-transitory computer readable medium comprising computer readable code executable by one or more processors to:
capture image data of an environment;
detect, in the image data, a first portion of the image data comprising an object which moves in the environment, and a second portion of the image data;
obtain a first geometric representation of the object;
communicate, to a playback device, the representation of the object without the second portion of the image data, wherein the first geometric representation of the object is configured to be rendered over a representation of the second portion of the image data.
9 . The non-transitory computer readable medium of claim 8 , wherein the representation of the second portion of the image data comprises a second geometric representation.
10 . The non-transitory computer readable medium of claim 9 , wherein the first geometric representation comprises one or more different data types than the second geometric representation.
11 . The non-transitory computer readable medium of claim 8 , wherein the representation of the second portion of the image data is generated from a plurality of images captured at different times.
12 . The non-transitory computer readable medium of claim 11 , wherein the computer readable code to generate the representation of the second portion of the image data comprises computer readable code to:
identify the object in a first image captured at a first time; and
replace the object in the first image with image content from a stable portion of a second image captured at a second time.
13 . The non-transitory computer readable medium of claim 8 , further comprising computer readable code to:
generate an updated representation of the object, wherein the updated representation is indicative of change in location of the object.
14 . The non-transitory computer readable medium of claim 8 , wherein the first geometric representation of the object comprises depth data.
15 . A system comprising:
one or more processors; and
one or more computer readable media comprising computer readable code executable by the one or more processors to:
capture image data of an environment;
detect, in the image data, a first portion of the image data comprising an object which moves in the environment, and a second portion of the image data;
obtain a first geometric representation of the object;
communicate, to a playback device, the representation of the object without the second portion of the image data, wherein the first geometric representation of the object is configured to be rendered over a representation of the second portion of the image data.
16 . The system of claim 15 , wherein the representation of the second portion of the image data comprises a second geometric representation.
17 . The system of claim 16 , wherein the first geometric representation comprises one or more different data types than the second geometric representation.
18 . The system of claim 15 , wherein the representation of the second portion of the image data is generated from a plurality of images captured at different times.
19 . The system of claim 18 , wherein the computer readable code to generate the representation of the second portion of the image data comprises computer readable code to:
identify the object in a first image captured at a first time; and
replace the object in the first image with image content from a stable portion of a second image captured at a second time.
20 . The system of claim 15 , wherein the first geometric representation of the object comprises depth data.