Compression standards have been used to reduce the cost of image storage and transmission for decades. In recent years, learned image compression methods have been proposed and achieved compelling performance to the traditional standards. However, in these methods, a set of different networks are used for various compression rates, resulting in a high cost in model storage and training. Although some variable-rate approaches have been proposed to reduce the cost by using a single network, most of them brought some performance degradation when applying fine rate control. To enable variable-rate control without sacrificing the performance, we propose an efficient Interpolation Variable-Rate (IVR) network, by introducing a handy Interpolation Channel Attention (InterpCA) module in the compression network. With the use of two hyperparameters for rate control and linear interpolation, the InterpCA achieves a fine PSNR interval of 0.001 dB and a fine rate interval of 0.0001 Bits-Per-Pixel (BPP) with 9000 rates in the IVR network. Experimental results demonstrate that the IVR network is the first variable-rate learned method that outperforms VTM 9.0 (intra) in PSNR and Multiscale Structural Similarity (MS-SSIM).
翻译:几十年来,一直采用压缩标准来降低图像存储和传输的成本,近些年来,已经提出了学习到的图像压缩方法,并达到了传统标准的令人信服的性能,然而,在这些方法中,对各种压缩率采用了一套不同的网络,导致模型存储和培训费用高昂。虽然已经提出一些可变率办法,通过使用单一网络降低成本,但多数在应用微调控制时带来了某种性能退化。为了在不牺牲性能的情况下实现可变率控制,我们提议在压缩网络中采用高效的 Indigation 变量-Rate(IVR) 网络,采用手动的 Interpica 频道注意模块(Interpica) 。在使用两个超度参数控制率和线性线性干涉时,Interpica 实现了0.001 dB和0.01 Bits- Per-Pixel(BPPPPPP) 的精度间隔,在IVR网络中采用9000的精度。实验结果表明,IVR网络是比VTMs-MS 9.0(In-S-S-Squal Statality)中的第一个可变率方法。