Selective Residual M-Net for Real Image Denoising
Β
Β
Β
Outline
Introduction
01
Related Work
02
Method
04
Conclusion
05
03
Experiment
01
Introduction
Method
02
Experiment
04
Conclusion
05
Related Work
03
Introduction
01
4
(1/2)
Β
Β
Β
Forward problem
Β
ill-posed problem
Β
Introduction
01
5
(2/2)
Outline
Introduction
01
Method
03
Experiment
04
Conclusion
05
Related Work
02
Introduction
01
Related Work
Experiment
04
Conclusion
05
02
Method
03
02
Related Work
8
(1/2)
Mehta, Raghav, and Jayanthi Sivaswamy. "M-net: A convolutional neural network for deep brain structure segmentation."Β 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). IEEE, 2017.
02
Related Work
9
(2/2)
Zamir, Syed Waqas, et al. "Learning enriched features for real image restoration and enhancement."Β European Conference on Computer Vision. Springer, Cham, 2020.
Li, Xiang, et al. "Selective kernel networks."Β Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019.
Outline
Introduction
01
Method
03
Experiment
04
Conclusion
05
Related Work
02
03
Method
Introduction
01
Related Work
02
Conclusion
05
Experiment
04
03
Method
12
(1/6)
03
Method
13
(2/6)
簑稱
03
Method
14
(3/6)
conv
conv
ReLU
conv
ReLU
conv
ReLU
1 x 1
conv
03
Method
15
(4/6)
03
Method
16
(5/6)
03
Method
17
(6/6)
Outline
Introduction
01
Method
03
Experiment
04
Conclusion
05
Related Work
02
04
Experiment
Introduction
01
Related Work
02
Conclusion
05
Method
03
Experiment
04
(1/5)
20
21
Experiment
04
(2/5)
22
Experiment
04
(3/5)
23
Experiment
04
(4/5)
24
Experiment
04
(5/5)
Outline
Introduction
01
Method
03
Experiment
04
Conclusion
05
Related Work
02
05
Conclusion
Introduction
01
Related Work
02
Experiment
04
Method
03
27
Conclusion
05
(1/1)
Thanks for Listening
SpeakerοΌChi-Mao Fan
Date : 2022.08.30