论文标题
基于GAN的可调图像压缩系统
A GAN-based Tunable Image Compression System
论文作者
论文摘要
重要性图的方法已在基于DNN的损耗图像压缩中广泛采用，以根据图像内容的重要性实现位分配。但是，在非重要区域的位分配不足通常会导致低BPP（每个像素位）的严重失真，从而阻碍了有效的含量加权图像压缩系统的发展。本文通过使用生成对抗网络（GAN）重建非重要区域来重新考虑基于内容的压缩。此外，将多尺度金字塔分解应用于编码器和歧视器，以实现高分辨率图像的全局压缩。本文还提出了可调压缩方案，以将图像压缩为任何特定的压缩率，而无需重新训练模型。实验结果表明，与最近报道的基于GAN的方法相比，我们提出的方法将MS-SSIM提高了10.3％以上，以实现Kodak数据集上相同的低BPP（0.05）。
The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insufficient allocation of bits in non-important regions often leads to severe distortion at low bpp (bits per pixel), which hampers the development of efficient content-weighted image compression systems. This paper rethinks content-based compression by using Generative Adversarial Network (GAN) to reconstruct the non-important regions. Moreover, multiscale pyramid decomposition is applied to both the encoder and the discriminator to achieve global compression of high-resolution images. A tunable compression scheme is also proposed in this paper to compress an image to any specific compression ratio without retraining the model. The experimental results show that our proposed method improves MS-SSIM by more than 10.3% compared to the recently reported GAN-based method to achieve the same low bpp (0.05) on the Kodak dataset.
