Abstract | ||
---|---|---|
In this work, we propose a deep learning-based method to improve the quality of JPEG images. Our proposed network predicts the compression loss of the JPEG image for compensating and restoring the image quality. To solve the color bleeding artifacts often found in JPEG image, our network considering it in our model and objective functions to restore the color channels. Our network is much lighter by using fewer parameters compared to other work, whereas our method can still provide satisfactory and well-restored images for JPEG images as demonstrated in our experiments. Even with the additional handling on the color channels, the number of parameters in our network model is still kept low around 224k. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISPACS48206.2019.8986361 | 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) |
Keywords | Field | DocType |
JPEG,compression artifacts removal,convolutional neural network,residual network,dilated convolution | Computer vision,Computer science,Convolutional neural network,Image quality,JPEG,Artificial intelligence,Color bleeding,Deep learning,Channel (digital image),Network model | Conference |
ISSN | ISBN | Citations |
2642-3510 | 978-1-7281-3039-2 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tien-Ying Kuo | 1 | 148 | 19.24 |
Yu-Jen Wei | 2 | 0 | 1.01 |
Chang-Hao Chao | 3 | 0 | 0.34 |