In this paper, we extend our prior research named DKIC and propose the perceptual-oriented learned image compression method, PO-DKIC. Specifically, DKIC adopts a dynamic kernel-based dynamic residual block group to enhance the transform coding and an asymmetric space-channel context entropy model to facilitate the estimation of gaussian parameters. Based on DKIC, PO-DKIC introduces PatchGAN and LPIPS loss to enhance visual quality. Furthermore, to maximize the overall perceptual quality under a rate constraint, we formulate this challenge into a constrained programming problem and use the Linear Integer Programming method for resolution. The experiments demonstrate that our proposed method can generate realistic images with richer textures and finer details when compared to state-of-the-art image compression techniques.

翻译：本文在先前名为DKIC的研究基础上，提出了一种面向感知的学习图像压缩方法PO-DKIC。具体而言，DKIC采用基于动态内核的动态残差块组来增强变换编码，并利用非对称空间-通道上下文熵模型来促进高斯参数的估计。基于DKIC，PO-DKIC引入PatchGAN和LPIPS损失以提升视觉质量。此外，为在码率约束下最大化整体感知质量，我们将该挑战形式化为约束规划问题，并采用线性整数规划方法进行求解。实验表明，与最先进的图像压缩技术相比，所提方法能生成具有更丰富纹理和更精细细节的逼真图像。