Sensitivity Decouple Learning for Image Compression Artifacts Reduction
- 1 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33, 3620-3633
Abstract
With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, i.e., the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrates the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.Keywords
Funding Information
- Key-Area Research and Development Program of Guangdong Province (2021B0101400002)
- National Natural Science Foundation of China (62088102, 62202010)
This publication has 70 references indexed in Scilit:
- Adaptive image coding efficiency enhancement using deep convolutional neural networksInformation Sciences, 2020
- Reduction of JPEG compression artifacts based on DCT coefficients predictionNeurocomputing, 2020
- AGARNet: Adaptively Gated JPEG Compression Artifacts Removal Network for a Wide Range Quality FactorIEEE Access, 2020
- One-To-Many Network for Visually Pleasing Compression Artifacts Reduction2017
- Learning Deep CNN Denoiser Prior for Image Restoration2017
- Building Dual-Domain Representations for Compression Artifacts Reduction2016
- D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images2016
- Deep Residual Learning for Image Recognition2016
- Autoencoder for wordsNeurocomputing, 2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009