论文标题
CompressNet：极低的比特率的生成压缩
CompressNet: Generative Compression at Extremely Low Bitrates
论文作者
论文摘要
在极低的比特率（<0.1 BPP）处的压缩图像一直是一项艰巨的任务，因为重建的质量大大降低了，因为对压缩数据分配的位数施加了强大的限制。随着越来越需要带有有限带宽的大量图像的需求，将图像压缩到非常低的尺寸是至关重要的任务。但是，现有方法在极低的比特率下无效。为了满足这一需求，我们提出了一个名为CompressNet的新颖网络，该网络通过开关预测网络（SAE-SPN）增强了堆叠的自动编码器。这有助于重建这些低比特率（<0.1 bpp）的视觉令人愉悦的图像。我们在CityScapes数据集上基准了我们提出的方法的性能，评估了极低的比特率的不同指标，以表明我们的方法的表现优于另一个最先进的方法。特别是，与深度学习的SOTA方法相比，在0.07的比特率为0.07时，降低了感知损失22％，而特里切特的启动距离（FID）降低了55％。
Compressing images at extremely low bitrates (< 0.1 bpp) has always been a challenging task since the quality of reconstruction significantly reduces due to the strong imposed constraint on the number of bits allocated for the compressed data. With the increasing need to transfer large amounts of images with limited bandwidth, compressing images to very low sizes is a crucial task. However, the existing methods are not effective at extremely low bitrates. To address this need, we propose a novel network called CompressNet which augments a Stacked Autoencoder with a Switch Prediction Network (SAE-SPN). This helps in the reconstruction of visually pleasing images at these low bitrates (< 0.1 bpp). We benchmark the performance of our proposed method on the Cityscapes dataset, evaluating over different metrics at extremely low bitrates to show that our method outperforms the other state-of-the-art. In particular, at a bitrate of 0.07, CompressNet achieves 22% lower Perceptual Loss and 55% lower Frechet Inception Distance (FID) compared to the deep learning SOTA methods.
