JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer

TL;DR

This paper introduces DCTransformer, a novel DCT domain transformer model that effectively recovers JPEG quantized coefficients by capturing spatial and frequential correlations, handling various quality factors, and aligning luminance and chrominance components.

Contribution

The paper proposes a dual-branch DCT domain transformer with quantization matrix embedding and luminance-chrominance alignment for improved JPEG artifact removal.

Findings

Outperforms current state-of-the-art JPEG artifact removal methods.

Effectively handles a wide range of compression quality factors.

Successfully recovers sparse quantized coefficients and color components.

Abstract

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.