Thousand to One: Semantic Prior Modeling for Conceptual Coding
| Autor: | Chang, Jianhui, Zhao, Zhenghui, Yang, Lingbo, Jia, Chuanmin, Zhang, Jian, Ma, Siwei |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Conceptual coding has been an emerging research topic recently, which encodes natural images into disentangled conceptual representations for compression. However, the compression performance of the existing methods is still sub-optimal due to the lack of comprehensive consideration of rate constraint and reconstruction quality. To this end, we propose a novel end-to-end semantic prior modeling-based conceptual coding scheme towards extremely low bitrate image compression, which leverages semantic-wise deep representations as a unified prior for entropy estimation and texture synthesis. Specifically, we employ semantic segmentation maps as structural guidance for extracting deep semantic prior, which provides fine-grained texture distribution modeling for better detail construction and higher flexibility in subsequent high-level vision tasks. Moreover, a cross-channel entropy model is proposed to further exploit the inter-channel correlation of the spatially independent semantic prior, leading to more accurate entropy estimation for rate-constrained training. The proposed scheme achieves an ultra-high 1000x compression ratio, while still enjoying high visual reconstruction quality and versatility towards visual processing and analysis tasks. Comment: ICME 2021 ORAL accepted |
| Databáze: | arXiv |
| Externí odkaz: |
|