ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Context-adaptive Entropy Model for End-to-end Optimized Image Compression
Cited 53 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
이주영, 조승현, 백승권
발행일
201905
출처
International Conference on Learning Representations (ICLR) 2019, pp.1-20
협약과제
18HR2300, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
초록
We propose a context-adaptive entropy model for use in end-to-end optimized image compression. Our model exploits two types of contexts, bit-consuming contexts and bit-free contexts, distinguished based upon whether additional bit allocation is required. Based on these contexts, we allow the model to more accurately estimate the distribution of each latent representation with a more generalized form of the approximation models, which accordingly leads to an enhanced compression performance. Based on the experimental results, the proposed method outperforms the traditional image codecs, such as BPG and JPEG2000, as well as other previous artificial-neural-network (ANN) based approaches, in terms of the peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) index. The test code is publicly available at https://github.com/JooyoungLeeETRI/CA_Entropy_Model.
KSP 제안 키워드
Approximation model, Compression performance, End to End(E2E), Entropy model, Image Compression, Multi-scale, Neural networks, Peak-Signal-to-Noise-Ratio(PSNR), Signal noise ratio(SNR), Structure Similarity Index measure(SSIM), bit allocation