Registered
METHOD AND APPARATUS FOR IMAGE PROCESSING USING CONTEXT-ADAPTIVE ENTROPY MODEL
- Inventors
-
Lee Jooyoung, Cho Seunghyun, Beack Seung Kwon, Kim Jongho, Jinwuk Seok, Kim Younhee, Jeong Se Yoon, Woong Lim, Hyunsuk Ko, Choi Jin Soo, Kim Hui Yong
- Application No.
-
16585658 (2019.09.27)
- Publication No.
-
20200107023 (2020.04.02)
- Registration No.
- 11412225 (2022.08.09)
- Country
- UNITED STATES
- Project Code
-
18HR2300, Development of Audio/Video Coding and Light Field Media Fundamental Technologies for Ultra Realistic Tera-media,
Choi Jin Soo
- Abstract
- Disclosed herein is a context-adaptive entropy model for end-to-end optimized image compression. The entropy model exploits two types of contexts. The two types of contexts are a bit-consuming context and a bit-free context, respectively, and these contexts are classified depending on the corresponding context requires the allocation of additional bits. Based on these contexts, the entropy model may more accurately estimate the distribution of each latent representation using a more generalized form of entropy models, thus improving compression performance.
- KSP Keywords
- Compression performance, End to End(E2E), Entropy model, Image processing(IP), context adaptive, image Compression