	US 12,437,354 B2
	Method for watermarking depth image based on mixed frequency-domain channel attention
Qiang Zhang, Dalian (CN); Bin Wang, Dalian (CN); Jun Tan, Dalian (CN); Rongrong Chen, Dalian (CN); and Xiaopeng Wei, Dalian (CN)
Assigned to DALIAN UNIVERSITY, Liaoning (CN)
Filed by DALIAN UNIVERSITY, Dalian (CN)
Filed on Aug. 22, 2023, as Appl. No. 18/453,846.
Application 18/453,846 is a continuation of application No. PCT/CN2023/101599, filed on Jun. 21, 2023.
Claims priority of application No. 202210955381.3 (CN), filed on Aug. 10, 2022.
Prior Publication US 2024/0054594 A1, Feb. 15, 2024
Int. Cl. G06T 1/00 (2006.01); G06T 3/40 (2024.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01)

CPC G06T 1/0028 (2013.01) [G06T 3/40 (2013.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01)]

8 Claims

1. A method for watermarking depth image based on mixed frequency-domain channel attention, comprising the following steps of:

step 1: a watermark information processor generating a watermark information feature map;

step 2: an encoder generating a watermarked image from a carrier image and a watermark information feature map;

step 3: a noise layer taking the watermarked image as an input, and generating a noise image through simulated differentiable noise;

step 4: a decoder down-sampling the noise image to recover watermark information;

step 5: a countermeasure discriminator classifying the carrier image and the watermarked image such that the encoder generates a watermarked image with a high quality.