We propose a learning-based compression scheme that envelopes a standard codec between pre and post-processing deep CNNs. Specifically, we demonstrate improvements over prior approaches utilizing a compression-decompression network by introducing: (a) an edge-aware loss function to prevent blurring that is commonly occurred in prior works & (b) a super-resolution convolutional neural network (CNN) for post-processing along with a corresponding pre-processing network for improved rate-distortion performance in the low rate regime. The algorithm is assessed on a variety of datasets varying from low to high resolution namely Set 5, Set 7, Classic 5, Set 14, Live 1, Kodak, General 100, CLIC 2019. When compared to JPEG, JPEG2000, BPG, and recent CNN approach, the proposed algorithm contributes significant improvement in PSNR with an approximate gain of 20.75%, 8.47%, 3.22%, 3.23% and 24.59%, 14.46%, 10.14%, 8.57% at low and high bit-rates respectively. Similarly, this improvement in MS-SSIM is approximately 71.43%, 50%, 36.36%, 23.08%, 64.70% and 64.47%, 61.29%, 47.06%, 51.52%, 16.28% at low and high bit-rates respectively. With CLIC 2019 dataset, PSNR is found to be superior with approximately 16.67%, 10.53%, 6.78%, and 24.62%, 17.39%, 14.08% at low and high bit-rates respectively, over JPEG2000, BPG, and recent CNN approach. Similarly, the MS-SSIM is found to be superior with approximately 72%, 45.45%, 39.13%, 18.52%, and 71.43%, 50%, 41.18%, 17.07% at low and high bit-rates respectively, compared to the same approaches. A similar type of improvement is achieved with other datasets also.

翻译：我们提出了一种基于学习的压缩方案，该方案在标准编解码器前后嵌入深度CNN进行预处理和后处理。具体而言，我们通过引入以下创新改进了现有压缩-解压网络方法：(a)边缘感知损失函数，用于防止先前工作中常见的模糊问题；(b)超分辨率卷积神经网络(CNN)作为后处理模块，并配以相应的预处理网络，以提升低码率下的率失真性能。该算法在Set 5、Set 7、Classic 5、Set 14、Live 1、Kodak、General 100、CLIC 2019等多个低分辨率至高分辨率数据集上进行了评估。与JPEG、JPEG2000、BPG及近期CNN方法相比，所提算法在PSNR指标上实现了显著提升：低码率与高码率下分别获得约20.75%、8.47%、3.22%、3.23%和24.59%、14.46%、10.14%、8.57%的增益。类似地，MS-SSIM指标的改进幅度在低码率与高码率下分别约为71.43%、50%、36.36%、23.08%、64.70%和64.47%、61.29%、47.06%、51.52%、16.28%。在CLIC 2019数据集上，与JPEG2000、BPG及近期CNN方法相比，所提算法在PSNR上表现出优势：低码率与高码率下分别提升约16.67%、10.53%、6.78%和24.62%、17.39%、14.08%。同样，在MS-SSIM指标上，相较于同类方法，低码率与高码率下分别提升约72%、45.45%、39.13%、18.52%和71.43%、50%、41.18%、17.07%。其他数据集也获得了类似程度的性能提升。