Registered
METHOD AND DEVICE FOR COMPRESSING IMAGE AND NEURAL NETWORK USING HIDDEN VARIABLE
- Inventors
-
Lee Jooyoung, Cho Seunghyun, Woong Lim, Kim Younhee, Jinwuk Seok, Sung-Chang Lim, Jeong Se Yoon, Dae Yeol Lee, Kim Jongho, Kim Hui Yong, Choi Jin Soo
- Application No.
-
16760609 (2018.10.30)
- Publication No.
-
20200351509 (2020.11.05)
- Registration No.
- 11477468 (2022.10.18)
- Country
- UNITED STATES
- Project Code
-
17HR2200, Development of Audio/Video Coding and Light Field Media Fundamental Technologies for Ultra Realistic Tera-media,
Choi Jin Soo
- Abstract
- A method and apparatus for image compression using a latent variable are provided. The multiple components of the latent variable may be sorted in order of importance. Through sorting, when the feature information of only some of the multiple components is used, the quality of a reconstructed image may be improved. In order to generate a latent variable, the components of which are sorted in order of importance, learning may be performed in various manners. Also, less important information may be eliminated from the latent variable, and processing, such as quantization, may be applied to the latent variable. Through elimination and processing, the amount of data for the latent variable may be reduced.
- KSP Keywords
- Feature information, Hidden variable, Image Compression, Latent Variable, Multiple components, neural network, reconstructed image
- Family
-