Thông tin tài liệu
Thông tin siêu dữ liệu biểu ghi
| Trường DC | Giá trị | Ngôn ngữ |
|---|---|---|
| dc.contributor.author | Xu, Zhigang | - |
| dc.contributor.author | Zhang, Chenmin | - |
| dc.contributor.author | Wu, Yanpeng | - |
| dc.date.accessioned | 2023-08-25T07:50:34Z | - |
| dc.date.available | 2023-08-25T07:50:34Z | - |
| dc.date.issued | 2023 | - |
| dc.identifier.uri | https://link.springer.com/article/10.1186/s40494-023-01015-1 | - |
| dc.identifier.uri | https://dlib.phenikaa-uni.edu.vn/handle/PNK/8956 | - |
| dc.description | CC-BY | vi |
| dc.description.abstract | Located in Dunhuang, northwest China, the Mogao Grottoes are a cultural treasure of China and the world. However, after more than 2000 years of weathering and destruction, many murals faded and were damaged. This treasure of human art is in danger. Mural inpainting through deep learning can permanently preserve mural information. Therefore, a digital restoration method combining the Deformable Convolution (DCN), ECANet, ResNet and Cycle Generative Adversarial Network (CycleGAN) is proposed. We name it DC-CycleGAN. Compared with other image digital inpainting methods, the proposed DC-CycleGAN based mural image color inpainting method has better inpainting effects and higher model performance. | vi |
| dc.language.iso | en | vi |
| dc.publisher | Springer | vi |
| dc.subject | CycleGAN | vi |
| dc.subject | DC-CycleGAN | vi |
| dc.title | Digital inpainting of mural images based on DC-CycleGAN | vi |
| dc.type | Book | vi |
| Bộ sưu tập | ||
| OER - Khoa học Vật liệu, Ứng dụng | ||
Danh sách tệp tin đính kèm:
