VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1137
Title: | End-to-end deep network for image denoising and colorization | Authors: | Khoa Van Tran Dinh Quang Vinh Phuc Hong Nguyen Narayan DEBNATH C Nguyen Tuan Duc Chang Wook Ahn |
Keywords: | Image denoising;Colorization;Deep network | Issue Date: | 2020 | Source: | http://manuscriptlink-society-file.s3.amazonaws.com/kism/conference/sma2020/presentation/SMA-2020_paper_39.pdf | Conference name: | The 9th International Conference on Smart Media and Application | Abstract: | This paper proposes a deep neural network that solves the denoising and colorization problem simultaneously. The joint problem is solved by two separate sub-networks that are trained in an end-to-end manner. Specifically, map attention modules are used to revise feature maps, while a few convolutional layers to extract features at the beginning of the network helps to boost the proposed network significantly. We use KITTI dataset to prepare training and testing datasets. In addition, we compare the proposed method with the baseline method using the PSNR and SSIM metrics. To have a fair comparison, we train the proposed and baseline methods using the same dataset, loss function, and training configurations. The experimental results show that the proposed method performed significantly better the baseline method in the KITTI dataset |
Duration: | 17-19/9/2020 | Conference venue: | Jeju, Korea | URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/1137 |
Appears in Collections: | Conference papers |
Show full item record
Items are protected by © Copyright of Vietnamese - German University Library