Abstract | ||
---|---|---|
Capturing images under high ISO mode introduces much noise. The statistics of high ISO noise is quite different from that of Gaussian noise. Therefore, this kind of noise is difficult to be removed by traditional Gaussian noise removal methods. This paper proposes a convolutional neural network (CNN) based method to jointly estimate and remove high ISO noise. There are two contributions in this paper. First, we propose a CNN based noise estimation method to estimate the pixel-wise noise level. Due to the Bayer down-sampling process in imaging, the noise variance map is characterized by Bayer patterns. Therefore, we propose packing 2 × 2 blocks in a noisy image into 4D vectors, which makes the pixels with similar noise levels be neighbors. Second, the noise variance map is correlated with the image content. Thus, we propose concatenating the estimated noise variance map with the noisy image, and feed the fused data to the denoising network. The two networks are trained together in an end-to-end fashion. Experimental results demonstrate that the proposed method outperforms state-of-the-art noise estimation and removal methods. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ICPR.2018.8545410 | 2018 24th International Conference on Pattern Recognition (ICPR) |
Keywords | Field | DocType |
noisy image,image content,estimated noise variance map,high ISO JPEG images,high ISO noise,convolutional neural network based method,CNN based noise estimation method,denoising network,4D vectors,Bayer patterns,Bayer down-sampling process,high ISO mode,deep joint noise removal,deep joint noise estimation,pixel-wise noise level estimation | Noise reduction,Computer vision,Noise measurement,Pattern recognition,Convolutional neural network,Computer science,Noise level,JPEG,Artificial intelligence,Concatenation,Pixel,Gaussian noise | Conference |
ISSN | ISBN | Citations |
1051-4651 | 978-1-5386-3789-0 | 0 |
PageRank | References | Authors |
0.34 | 9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huanjing Yue | 1 | 24 | 6.89 |
Shengdi Zhou | 2 | 0 | 0.34 |
Jingyu Yang | 3 | 274 | 31.04 |
Xiao-Yan Sun | 4 | 1000 | 85.94 |
Chunping Hou | 5 | 85 | 14.69 |