Back to results
US 10,832,487 B1Granted
Depth map generation
AssigneeApple Inc.
InventorsDaniel Ulbricht, Amit Kumar K C, Angela Blechschmidt, Chen-Yu Lee, Eshan Verma, Mohammad Haris Baig, Tanmay Batra
Life of this patent
Estimating the term…
Abstract
In one implementation, a method of generating a depth map is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes generating, based on a first image and a second image, a first depth map of the second image. The method includes generating, based on the first depth map of the second image and pixel values of the second image, a second depth map of the second image.
Claims20
A method comprising:
- capturing, from a first perspective, a first image of a scene;
- capturing, from a second perspective different than the first perspective, a second image of the scene, the second image including a plurality of second pixels having a respective plurality of second pixel values;
- generating, based on the first image and the second image, a first depth map of the second image including, for each of a subset of the plurality of second pixels, a depth of the scene for the respective second pixel;
- generating, based on the first depth map of the second image and the respective plurality of second pixel values, a second depth map of the second image including, for each of the respective plurality of second pixels, a depth of the scene for the respective second pixel;
- capturing a third image of the scene, the third image including a plurality of third pixels having a respective plurality of third pixel values;
- and
- generating, based on the second depth map of the second image and the third image, a first depth map of the third image including, for each of a subset of the plurality of third pixels, a depth of the scene for the respective third pixel.
4 more elements
A device comprising:
- one or more scene cameras;
- and
- one or more processors to:
- capture, from a first perspective using the one or more scene cameras;
- capture, from a second perspective different than the first perspective using the one or more scene cameras, a second image of the scene, the second image including a plurality of second pixels having a respective plurality of second pixel values;
- generate, based on the first image and the second image, a first depth map of the second image including, for each of a subset of the plurality of second pixels, a depth of the scene for the respective second pixel;
- generate, based on the first depth map of the second image and the respective plurality of second pixel values, a second depth map of the second image including, for each of the respective plurality of second pixels, a depth of the scene for the respective second pixel;
- capture, using the one or more scene cameras, a third image of the scene, the third image including a plurality of third pixels having a respective plurality of third pixel values;
- and
- generate, based on the second depth map of the second image and the third image, a first depth map of the third image including, for each of a subset of the plurality of third pixels, a depth of the scene for the respective third pixel.
7 more elements
A non-transitory computer-readable medium having instructions encoded thereon which, when executed by one or more processors of a device including one or more scene cameras, cause the device to:
- capture, from a first perspective, a first image of a scene;
- capture, from a second perspective different than the first perspective, a second image of the scene, the second image including a plurality of second pixels having a respective plurality of second pixel values;
- generate, based on the first image and the second image, a first depth map of the second image including, for each of a subset of the plurality of second pixels, a depth of the scene for the respective second pixel;
- generate, based on the first depth map of the second image and the respective plurality of second pixel values, a second depth map of the second image including, for each of the respective plurality of second pixels, a depth of the scene for the respective second pixel;
- capture a third image of the scene, the third image including a plurality of third pixels having a respective plurality of third pixel values;
- and
- generate, based on the second depth map of the second image and the third image, a first depth map of the third image including, for each of a subset of the plurality of third pixels, a depth of the scene for the respective third pixel.
4 more elements
Dependencies are inferred from the claim text.