Abstract | ||
---|---|---|
Discriminative learning based denoising model trained with Additive White Gaussian Noise (AWGN) performs well on synthesized noise. However, realistic noise can be spatial-variant, signal-dependent and a mixture of complicated noises. In this paper, we explore multiple strategies for applying an AWGN-based denoiser to realistic noise. Specifically, we trained a deep network integrating noise estimating and denoiser with mixed Gaussian (AWGN) and Random Value Impulse Noise (RVIN). To adapt the model to realistic noises, we investigated multi-channel, multi-scale and super-resolution approaches. Our preliminary results demonstrated the effectiveness of the newly-proposed noise model and adaptation strategies. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1609/aaai.v33i01.330110085 | AAAI |
Field | DocType | Volume |
Noise reduction,Computer science,Speech recognition,Gaussian,Impulse noise,Artificial intelligence,Additive white Gaussian noise,Machine learning,Discriminative learning | Conference | 33 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuqian Zhou | 1 | 34 | 5.93 |
Jiao Jianbo | 2 | 63 | 9.88 |
Haibin Huang | 3 | 172 | 12.21 |
Jue Wang | 4 | 2871 | 155.89 |
Thomas S. Huang | 5 | 27815 | 2618.42 |