Antonio José G. Busson
Paulo Renato C. Mendes
Daniel de S. Moraes
Álan Lívio V. Guedes
ABSTRACT
Many recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a JPEG image decoder that is purely based on the frequency-to-frequency domain: it reads the quantized DCT coefficients received from a low-quality image bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same image with enhanced quality. In experiments with two datasets, our best model was able to improve from images with quantized DCT coefficients corresponding to a Qualityz Factor (QF) of 10 to enhanced quality images with QF slightly higher than 20.
- Carlo "zED" Caputo. 2008. Optimization of Video Compression Parameters through Genetic Algorithms. In Companion Proceedings of the XIV Brazilian Symposium on Multimedia and the Web (Vila Velha, Espírito Santo, Brazil) (WebMedia '08). Association for Computing Machinery, New York, NY, USA, 33--36. https://doi.org/10.1145/1809980.1809990Google Scholar
Digital Library
- Chao Dong, Yubin Deng, Chen Change Loy, and Xiaoou Tang. 2015. Compression artifacts reduction by a deep convolutional network. In Proceedings of the IEEE International Conference on Computer Vision. 576--584.Google ScholarDigital Library
- Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2015. Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence 38, 2 (2015), 295--307.Google Scholar
- Joint Photographic Experts Group et al. 2004. JPEG standards: ISO/IEC IS 10918-1, ITU-T Recommendation T.81.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Jingru Hou, Yujuan Si, and Liangliang Li. 2019. Image Super-Resolution Reconstruction Method Based on Global and Local Residual Learning. In 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC). IEEE, 341--348.Google Scholar
- N Instruments. 2013. Peak signal-to-noise ratio as an image quality metric.Google Scholar
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015).Google ScholarDigital Library
- Hossam M Kasem, Kwok-Wai Hung, and Jianmin Jiang. 2018. Revised Spatial Transformer Network towards Improved Image Super-resolutions. In 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 2688--2692.Google ScholarCross Ref
- T. Kim, H. Lee, H. Son, and S. Lee. 2019. SF-CNN: A Fast Compression Artifacts Removal via Spatial-To-Frequency Convolutional Neural Networks. In 2019 IEEE International Conference on Image Processing (ICIP). 3606--3610.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4681--4690.Google ScholarCross Ref
- Sheng Li, Fengxiang He, Bo Du, Lefei Zhang, Yonghao Xu, and Dacheng Tao. 2019. Fast spatio-temporal residual network for video super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 10522--10531.Google ScholarCross Ref
- Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. 2017. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 136--144.Google ScholarCross Ref
- Bumjun Park, Songhyun Yu, and Jechang Jeong. 2019. Densely connected hierarchical network for image denoising. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.Google ScholarCross Ref
- RajeshMehra Pinki. 2016. Estimation of the image quality under different distortions. International Journal of Engineering and Computer Science 5, 7 (2016), 17291--17296.Google Scholar
- Bulla Rajesh, Mohammed Javed, Ratnesh, and Shubham Srivastava. 2019. DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients. arXiv:cs.CV/1907.11503Google Scholar
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234--241.Google ScholarCross Ref
- Gabriel N. P. dos Santos, Pedro V. A. de Freitas, Antonio José G Busson, Álan LV Guedes, Ruy Milidiú, and Sérgio Colcher. 2019. Deep learning methods for video understanding. In Proceedings of the 25th Brazillian Symposium on Multimedia and the Web. 21--23. https://doi.org/10.1145/3323503.3345029Google ScholarDigital Library
- Vinay Verma, Nikita Agarwal, and Nitin Khanna. 2018. DCT-domain deep convolutional neural networks for multiple JPEG compression classification. Signal Processing: Image Communication 67 (2018), 22--33.Google ScholarCross Ref
- John Watkinson. 2004. The MPEG Handbook: MPEG-1, MPEG-2, MPEG-4. Taylor & Francis.Google Scholar
- Qi Ye, Shanxin Yuan, and Tae-Kyun Kim. 2016. Spatial attention deep net with partial pso for hierarchical hybrid hand pose estimation. In European conference on computer vision. Springer, 346--361.Google ScholarCross Ref
- Ke Yu, Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016. Deep convolution networks for compression artifacts reduction. arXiv preprint arXiv:1608.02778 (2016).Google Scholar
- Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing 26, 7 (2017), 3142--3155.Google ScholarDigital Library
- Xiaoshuai Zhang, Wenhan Yang, Yueyu Hu, and Jiaying Liu. 2018. Dmcnn: Dual-domain multi-scale convolutional neural network for compression artifacts removal. In 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 390--394.Google ScholarCross Ref
- Leilei Zhu, Shu Zhan, and Haiyan Zhang. 2019. Stacked U-shape networks with channel-wise attention for image super-resolution. Neurocomputing 345 (2019), 58--66.Google ScholarDigital Library
Index Terms
- Decoder-Side Quality Enhancement of JPEG Images Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients
Recommendations
Deep Learning Approach to the Quality Restoration for JPEG Images
ICCCM '22: Proceedings of the 10th International Conference on Computer and Communications ManagementThe JPEG codec is still the dominant and common image compression format despite the continuous development of new image compression techniques. In order to raise the compression ratio, distortion caused by some quantization operation within the ...
An Approach for Color Image Compression of JPEG and PNG Images Using DCT and DWT
CICN '14: Proceedings of the 2014 International Conference on Computational Intelligence and Communication NetworksNow a days image compression has become is an indispensible part of digitized image storage and transmission. Compression of an image is necessary before storing and transmitting it due to its limitation of storage and bandwidth capacity. Wavelet ...
On performance of lossless compression for HDR image quantized in color space
High dynamic range (HDR) image requires a higher number of bits per color channel than traditional images. This brings about problems to storage and transmission. Color space quantization has been extensively studied to achieve bit encodings for each ...
Comments