US 11,869,171 B2
Adaptive deformable kernel prediction network for image de-noising
Anbang Yao, Beijing (CN); Ming Lu, Beijing (CN); Yikai Wang, Beijing (CN); Xiaoming Chen, Shanghai (CN); Junjie Huang, Guangdong (CN); Tao Lv, Shanghai (CN); Yuanke Luo, Shanghai (CN); Yi Yang, Shanghai (CN); Feng Chen, Shanghai (CN); Zhiming Wang, Shanghai (CN); Zhiqiao Zheng, Guangdong Sheng (CN); and Shandong Wang, Beijing (CN)
Assigned to INTEL CORPORATION, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Nov. 5, 2020, as Appl. No. 17/090,170.
Claims priority of application No. 201911081492.0 (CN), filed on Nov. 7, 2019.
Prior Publication US 2021/0142448 A1, May 13, 2021
Int. Cl. G06T 5/00 (2006.01); G06N 3/04 (2023.01)
CPC G06T 5/002 (2013.01) [G06N 3/04 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method comprising:
de-noising an image by a convolutional neural network implemented on a compute hardware engine, the image including a plurality of pixels,
for each of the plurality of pixels of the image, generating a convolutional kernel having a plurality of kernel values for the pixel;
generating a plurality of offsets for the pixel respectively corresponding to the plurality of kernel values, each of the plurality of offsets to indicate a deviation from a pixel position of the pixel, wherein an upper limit of the deviation is predefined;
determining a plurality of deviated pixel positions based on the pixel position of the pixel and the plurality of offsets, wherein an offset of the plurality of offsets comprises a position value to indicate the deviation from the pixel position of the pixel, wherein the position value comprises floating point values, wherein the plurality of kernel values are different for at least two pixels of the image; and
filtering the pixel with the convolutional kernel and pixel values of the plurality of deviated pixel positions to obtain a de-noised pixel.