US 11,861,854 B2
Dense feature scale detection for image matching
Shenlong Wang, Toronto (CA); Linjie Luo, Los Angeles, CA (US); Ning Zhang, Los Angeles, CA (US); and Jia Li, Marina Del Rey, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on May 26, 2022, as Appl. No. 17/825,994.
Application 17/825,994 is a continuation of application No. 16/721,483, filed on Dec. 19, 2019, granted, now 11,367,205.
Application 16/721,483 is a continuation of application No. 15/712,990, filed on Sep. 22, 2017, granted, now 10,552,968.
Claims priority of provisional application 62/399,171, filed on Sep. 23, 2016.
Prior Publication US 2022/0292697 A1, Sep. 15, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/246 (2017.01); G06T 7/33 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01); G06T 7/40 (2017.01)
CPC G06T 7/248 (2017.01) [G06T 7/33 (2017.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 7/40 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying, using one or more processors of a machine, an image;
generating a plurality of scaled images from the image;
generating image features for the plurality of scaled images using one or more convolutional neural networks;
generating an attention map based on texture data of pixels of the image using the one or more convolutional neural networks;
generating dense features by combining image features with attention values of the attention map;
identifying, using the dense features, a location within one or more images of an object depicted in each of the one or more images; and
generating one or more modified images from the one or more images using the location of the object in the one or more images.