Abstract | ||
---|---|---|
•A progressive GAN generation framework based on GANs is proposed to generate highresolution ground-view panorama images solely from low-resolution aerial images.•A novel cross-stage attention module is proposed to bridge adjacent generation stages of the progressive generation process so that the quality of synthesized panorama image could be continually improved.•A novel orientation-aware data augmentation strategy is proposed to utilize geometric relation between aerial and segmentation images for model training.•The proposed model establishes new state-of-the-art results for the task of cross-view panorama scene image synthesis in two scenarios: suburb area and urban area. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2022.108884 | Pattern Recognition |
Keywords | DocType | Volume |
Progressive attention GANs,Cross-view panorama image synthesis,Cross-stage attention,Orientation-aware data augmentation,Multi-stage image generation | Journal | 131 |
Issue | ISSN | Citations |
1 | 0031-3203 | 1 |
PageRank | References | Authors |
0.35 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Songsong Wu | 1 | 29 | 5.86 |
Hao Tang | 2 | 338 | 34.83 |
Xiao-Yuan Jing | 3 | 769 | 55.18 |
Jianjun Qian | 4 | 382 | 27.74 |
Nicu Sebe | 5 | 7013 | 403.03 |
Yan Yan | 6 | 691 | 31.13 |
Qing-Hua Zhang | 7 | 11 | 5.26 |