Cross-view panorama image synthesis with progressive attention GANs

Highlights：

• 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.

摘要

•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.

论文关键词：Progressive attention GANs,Cross-view panorama image synthesis,Cross-stage attention,Orientation-aware data augmentation,Multi-stage image generation

论文评审过程：Received 10 October 2020, Revised 25 June 2022, Accepted 30 June 2022, Available online 3 July 2022, Version of Record 8 July 2022.