With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction,ie, the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.

翻译：受益于深度学习技术，近年来在图像压缩伪影降低方面取得了显著进展。尽管现有方法的性能有所提升，但它们仅关注学习从压缩图像到原始图像的映射，而忽略了给定压缩图像的内在属性，这极大地损害了下游解析任务的性能。与这些方法不同，我们提出将内在属性解耦为两种互补特征用于伪影降低，即：用于训练期间正则化高层语义表示的压缩不敏感特征，以及用于感知压缩程度的压缩敏感特征。为实现这一目标，我们首先采用对抗训练来正则化压缩特征和原始编码特征，以保留高层语义；随后，我们开发了面向压缩质量感知的特征编码器，用于提取压缩敏感特征。基于这两种互补特征，我们提出了双感知引导网络（Dual Awareness Guidance Network，DAGN），在解码阶段将这些感知特征作为变换引导。在我们的DAGN中，我们设计了跨特征融合模块，通过将压缩不敏感特征融合到伪影降低基线中，以保持其一致性。我们的方法在BSD500数据集上平均获得了2.06 dB的PSNR增益，超越了当前最先进的方法，并且处理单张BSD500图像仅需29.7毫秒。此外，在LIVE1和LIU4K数据集上的实验结果也证明了该方法在量化指标、视觉质量以及下游机器视觉任务方面的效率、有效性和优越性。