Variable Rate Image Compression Method with Dead-zone Quantizer
| Autor: | Kimihiko Kazui, Akira Nakagawa, Tan Zhiming, Wen Sihan, Keizo Kato, Zhou Jing |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Structural similarity
Computer science business.industry Deep learning Quantization (signal processing) Image and Video Processing (eess.IV) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Data_CODINGANDINFORMATIONTHEORY Electrical Engineering and Systems Science - Image and Video Processing Autoencoder FOS: Electrical engineering electronic engineering information engineering Codec Orthonormal basis Artificial intelligence business Algorithm Image compression |
| Zdroj: | CVPR Workshops |
| Popis: | Deep learning based image compression methods have achieved superior performance compared with transform based conventional codec. With end-to-end Rate-Distortion Optimization (RDO) in the codec, compression model is optimized with Lagrange multiplier $\lambda$. For conventional codec, signal is decorrelated with orthonmal transformation, and uniform quantizer is introduced. We propose a variable rate image compression method with dead-zone quantizer. Firstly, the autoencoder network is trained with RaDOGAGA \cite{radogaga} framework, which can make the latents isometric to the metric space, such as SSIM and MSE. Then the conventional dead-zone quantization method with arbitrary step size is used in the common trained network to provide the flexible rate control. With dead-zone quantizer, the experimental results show that our method performs comparably with independently optimized models within a wide range of bitrate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|