Quantization Guided JPEG Artifact Correction

@inproceedings{Ehrlich2020QuantizationGJ,
  title={Quantization Guided JPEG Artifact Correction},
  author={Max Ehrlich and Ser-Nam Lim and L. Davis and Abhinav Shrivastava},
  booktitle={ECCV},
  year={2020}
}
The JPEG image compression algorithm is the most popular method of image compression because of its ability for large compression ratios. However, to achieve such high compression, information is lost. For aggressive quantization settings, this leads to a noticeable reduction in image quality. Artifact correction has been studied in the context of deep neural networks for some time, but the current state-of-the-art methods require a different model to be trained for each quality setting… Expand
Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
Plug-and-Play Image Restoration with Deep Denoiser Prior

References

SHOWING 1-10 OF 54 REFERENCES
Compression Artifacts Reduction by a Deep Convolutional Network
Image quality assessment: from error visibility to structural similarity
Implicit Dual-Domain Convolutional Network for Robust Color Image Compression Artifact Reduction
Dmcnn: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Multi-level Wavelet-CNN for Image Restoration
Contour Detection and Hierarchical Image Segmentation
CAS-CNN: A deep convolutional neural network for image compression artifact suppression
SGDR: Stochastic Gradient Descent with Warm Restarts
...
1
2
3
4
5
...