In this paper, a unified transformation method in learned image compression(LIC) is proposed from the perspective of modulation. Firstly, the quantization in LIC is considered as a generalized channel with additive uniform noise. Moreover, the LIC is interpreted as a particular communication system according to the consistency in structures and optimization objectives. Thus, the technology of communication systems can be applied to guide the design of modules in LIC. Furthermore, a unified transform method based on signal modulation (TSM) is defined. In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation. A series of transformation methods, e.g. TPM and TJM, are obtained by extending to nonlinear modulation. The experimental results on various datasets and backbone architectures verify that the effectiveness and robustness of the proposed method. More importantly, it further confirms the feasibility of guiding LIC design from a communication perspective. For example, when backbone architecture is hyperprior combining context model, our method achieves 3.52$\%$ BD-rate reduction over GDN on Kodak dataset without increasing complexity.

翻译：本文从调制视角出发，提出了一种学习型图像压缩（LIC）中的统一变换方法。首先，将LIC中的量化视为带有加性均匀噪声的广义信道。其次，根据结构一致性和优化目标一致性，将LIC解释为一种特殊的通信系统。因此，通信系统技术可应用于指导LIC模块的设计。进一步地，定义了基于信号调制的统一变换方法（TSM）。从TSM视角看，现有变换方法在数学上可简化为线性调制；通过扩展至非线性调制，获得了TPM和TJM等一系列变换方法。在多种数据集和骨干架构上的实验结果验证了所提方法的有效性与鲁棒性。更重要的是，这进一步证实了从通信视角指导LIC设计的可行性。例如，当骨干架构为结合上下文模型的超先验结构时，本方法在Kodak数据集上相比GDN实现了3.52%的BD-rate降低，且未增加计算复杂度。