论文标题
量化引导JPEG伪影校正
Quantization Guided JPEG Artifact Correction
论文作者
论文摘要
JPEG图像压缩算法是最流行的图像压缩方法，因为它具有大型压缩比。但是，为了达到如此高的压缩，信息会丢失。对于积极的量化设置，这会导致图像质量明显降低。一段时间以来，已经在深层神经网络的背景下研究了伪像校正，但是当前的最新方法需要为每个质量设置培训不同的模型，从而极大地限制了其实际应用。我们通过创建一个由JPEG文件量化矩阵参数化的新颖体系结构来解决此问题。这使我们的单个模型能够比针对特定质量设置训练的模型实现最先进的性能。
The JPEG image compression algorithm is the most popular method of image compression because of its ability for large compression ratios. However, to achieve such high compression, information is lost. For aggressive quantization settings, this leads to a noticeable reduction in image quality. Artifact correction has been studied in the context of deep neural networks for some time, but the current state-of-the-art methods require a different model to be trained for each quality setting, greatly limiting their practical application. We solve this problem by creating a novel architecture which is parameterized by the JPEG files quantization matrix. This allows our single model to achieve state-of-the-art performance over models trained for specific quality settings.
