US 11,854,243 B2
Gaze correction of multi-view images
Eric Sommerlade, Oxford (GB); and Michael G. Robinson, Boulder, CO (US)
Assigned to RealD Spark, LLC, Boulder, CO (US)
Filed by RealD Spark, LLC, Beverly Hills, CA (US)
Filed on Mar. 24, 2022, as Appl. No. 17/703,039.
Application 17/703,039 is a continuation of application No. 16/937,382, filed on Jul. 23, 2020, granted, now 11,317,081.
Application 16/937,382 is a continuation of application No. 16/405,415, filed on May 7, 2019, granted, now 10,750,160, issued on Aug. 18, 2020.
Application 16/405,415 is a continuation of application No. 15/397,951, filed on Jan. 4, 2017, granted, now 10,321,123, issued on Jun. 11, 2019.
Claims priority of provisional application 62/274,897, filed on Jan. 5, 2016.
Prior Publication US 2022/0400246 A1, Dec. 15, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 7/14 (2006.01); G06V 10/62 (2022.01); G06F 3/01 (2006.01); H04N 7/15 (2006.01); G06V 10/46 (2022.01); G06V 40/18 (2022.01); H04N 13/344 (2018.01); H04N 13/117 (2018.01)
CPC G06V 10/62 (2022.01) [G06F 3/011 (2013.01); G06F 3/013 (2013.01); G06V 10/462 (2022.01); G06V 40/193 (2022.01); H04N 7/147 (2013.01); H04N 7/15 (2013.01); H04N 13/344 (2018.05); H04N 13/117 (2018.05)] 20 Claims
OG exemplary drawing
 
1. A method of adjusting multi-view images of a head to correct gaze, the method comprising:
for each image, using a processor to identify image patches containing the left and right eyes of the head, respectively;
in respect of the image patches containing the left eyes of the head in each image of the multi-view images, and also in respect of the image patches containing the right eyes of the head in each image of the multi-view images, using the processor to perform the steps of:
deriving a feature vector from plural local image descriptors of the image patch in at least one image of the multi-view images; and
deriving a displacement vector field representing a transformation of an image patch, using the derived feature vector to look up reference data comprising reference displacement vector fields associated with possible values of the feature vector; and
adjusting each image of the multi-view images by transforming the image patches containing the left and right eyes of the head in accordance with the derived displacement vector field.