Quantization Guided JPEG Artifact Correction
This solves a practical limitation in deploying artifact correction models for JPEG compression, making it more efficient and scalable for real-world applications.
The paper tackles the problem of JPEG artifact correction requiring separate models for each quality setting by introducing a novel architecture parameterized by the quantization matrix, enabling a single model to achieve state-of-the-art performance across settings.
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.