BROWSE
Detail
Conference Paper
Context-adaptive Entropy Model for End-to-end Optimized Image Compression
Cited 170 time in 
Share 
Share
- Authors
- Jooyoung Lee, Seunghyun Cho, Seung-Kwon Beack
- Issue Date
- 2019-05
- Citation
- International Conference on Learning Representations (ICLR) 2019, pp.1-20
- Language
- English
- Type
- Conference Paper
- Abstract
- 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 Keywords
- Approximation model, Compression performance, End to End(E2E), Entropy model, Multi-scale, Peak-Signal-to-Noise-Ratio(PSNR), Signal noise ratio(SNR), Structure Similarity Index measure(SSIM), bit allocation, context adaptive, image Compression