Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND ELECTRONIC DEVICE FOR PERFORMING AI BASED ZOOM OF IMAGE
Document Type and Number:
WIPO Patent Application WO/2021/182798
Kind Code:
A1
Abstract:
Embodiments herein provide a method for performing an AI based zoom of an image in an electronic device. The method includes receiving the image. The method includes obtaining, through a pixel domain Neural Network (NN) block, a first set of feature maps of the image based on pixels of the image. The method includes obtaining, through a frequency domain NN block, a second set of feature maps of the image based on frequencies of the image. The method includes generating a first set of feature maps and the second set of feature maps using ESBs at a lower computational complexity. The method includes generating, through a joint refinement NN block, a final image with a resolution higher than the image based on the first set of feature maps and the second set of feature maps.

Inventors:
PASUPULETI SIRISH KUMAR (IN)
GADDE RAJ NARAYANA (IN)
AKULA SRI NITCHITH (IN)
SAHA AVINAB (IN)
Application Number:
PCT/KR2021/002721
Publication Date:
September 16, 2021
Filing Date:
March 05, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06T3/40; G06T5/00; G06T7/13
Foreign References:
US20190220977A12019-07-18
US20200058106A12020-02-20
KR20140061028A2014-05-21
Other References:
CHEN YUANTAO, WANG JIN, CHEN XI, SANGAIAH ARUN KUMAR, YANG KAI, CAO ZHOUHONG: "Image Super-Resolution Algorithm Based on Dual-Channel Convolutional Neural Networks", APPLIED SCIENCES, vol. 9, no. 11, 2316, 5 June 2019 (2019-06-05), pages 1 - 16, XP055779877, DOI: 10.3390/app9112316
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: