Divakar, Nithish and Babu, R Venkatesh (2017) Image Denoising via CNNs: An Adversarial Approach. In: 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, 21 - 26 July 2017, Honolulu, pp. 1076-1083.
|
PDF
CVPRW 2017_1076-1083_2017.pdf - Published Version Download (1MB) | Preview |
Abstract
Is it possible to recover an image from its noisy version using convolutional neural networks? This is an interesting problem as convolutional layers are generally used as feature detectors for tasks like classification, segmentation and object detection. We present a new CNN architecture for blind image denoising which synergically combines three architecture components, a multi-scale feature extraction layer which helps in reducing the effect of noise on feature maps, an ℓp regularizer which helps in selecting only the appropriate feature maps for the task of reconstruction, and finally a three step training approach which leverages adversarial training to give the final performance boost to the model. The proposed model shows competitive denoising performance when compared to the state-of-the-art approaches.
| Item Type: | Conference Paper |
|---|---|
| Publisher: | IEEE Computer Society |
| Additional Information: | The copyright for this article belongs to the Authors. |
| Department/Centre: | Division of Interdisciplinary Sciences > Computational and Data Sciences |
| Date Deposited: | 09 Jun 2022 05:00 |
| Last Modified: | 09 Jun 2022 05:00 |
| URI: | https://eprints.iisc.ac.in/id/eprint/73194 |
Actions (login required)
 |
View Item |
