提出轻量级非对称图像压缩，解码器极简且性能接近VVC。
AsymLLIC: Asymmetric Lightweight Learned Image Compression
- 采用非对称结构，解码器模块可逐步替换为更简单设计。
- 解码器仅需51.47 GMACs计算和19.65M参数，性能媲美VVC。
- 适用于低功耗设备部署，可适配任意学习型图像压缩模型。
学习型图像压缩（LIC）方法通常采用对称的编码器与解码器结构，不可避免地增加了解码时间。但在实际应用中，更需要非对称设计：解码端需低复杂度以适配多样化的低端设备，而编码端可接受更高复杂度以提升压缩性能。本文提出一种非对称轻量级学习型图像压缩（AsymLLIC）架构及新型训练方案，支持将复杂解码模块逐步替换为更简单的模块。基于此方法，我们系统比较了多种解码网络结构，在复杂度与压缩性能间取得更好平衡。实验结果表明，所提方法不仅性能可比VVC，且解码器仅需51.47 GMACs计算量和19.65M参数。该设计范式可轻松应用于任意LIC模型，推动学习型图像压缩技术的实际部署。
原文摘要 · Abstract (English)
Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to cater to diverse low-end devices, while the encoder can accommodate higher complexity to improve coding performance. In this paper, we propose an asymmetric lightweight learned image compression (AsymLLIC) architecture with a novel training scheme, enabling the gradual substitution of complex decoding modules with simpler ones. Building upon this approach, we conduct a comprehensive comparison of different decoder network structures to strike a better trade-off between complexity and compression performance. Experiment results validate the efficiency of our proposed method, which not only achieves comparable performance to VVC but also offers a lightweight decoder with only 51.47 GMACs computation and 19.65M parameters. Furthermore, this design methodology can be easily applied to any LIC models, enabling the practical deployment of LIC techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。