JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer
This addresses the issue of image quality degradation in JPEG compression for applications like digital photography and media, but it is incremental as it builds on existing DCT domain methods.
The paper tackles the problem of recovering JPEG compressed images in the frequency domain, which often loses details due to quantization, by proposing a DCT domain spatial-frequential Transformer (DCTransformer) that outperforms state-of-the-art JPEG artifact removal techniques.
JPEG compression adopts the quantization of Discrete Cosine Transform (DCT) coefficients for effective bit-rate reduction, whilst the quantization could lead to a significant loss of important image details. Recovering compressed JPEG images in the frequency domain has recently garnered increasing interest, complementing the multitude of restoration techniques established in the pixel domain. However, existing DCT domain methods typically suffer from limited effectiveness in handling a wide range of compression quality factors or fall short in recovering sparse quantized coefficients and the components across different colorspaces. To address these challenges, we propose a DCT domain spatial-frequential Transformer, namely DCTransformer, for JPEG quantized coefficient recovery. Specifically, a dual-branch architecture is designed to capture both spatial and frequential correlations within the collocated DCT coefficients. Moreover, we incorporate the operation of quantization matrix embedding, which effectively allows our single model to handle a wide range of quality factors, and a luminance-chrominance alignment head that produces a unified feature map to align different-sized luminance and chrominance components. Our proposed DCTransformer outperforms the current state-of-the-art JPEG artifact removal techniques, as demonstrated by our extensive experiments.