# JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer

arXiv: https://arxiv.org/abs/2308.09110 · HTML: https://mlsanity.com/paper/2308.09110/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 62 references that are in the map.
- First posted on arXiv 17 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [Quantization Guided JPEG Artifact Correction](https://mlsanity.com/paper/2004.09320/) (2020)
- [Variational Deep Image Restoration](https://mlsanity.com/paper/2207.01074/) (2022)
- [DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal](https://mlsanity.com/paper/1806.03275/) (2018)
- [Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction](https://mlsanity.com/paper/1810.08042/) (2018)
- [Compression Artifacts Removal Using Convolutional Neural Networks](https://mlsanity.com/paper/1605.00366/) (2016)
- [Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal](https://mlsanity.com/paper/2009.06912/) (2020)
- [Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal](https://mlsanity.com/paper/2207.07335/) (2022)

## Built on by (most cited first, 3 of 3)

- [FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restoration](https://mlsanity.com/paper/2501.12832/) (2025)
- [LIPT: Latency-aware Image Processing Transformer](https://mlsanity.com/paper/2404.06075/) (2024)
- [Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations](https://mlsanity.com/paper/2506.21171/) (2025)

## Abstract (arXiv)

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.