Semantic-aware Network for Aerial-to-Ground Image Synthesis
This work addresses a challenging domain-specific problem in computer vision for applications like urban planning or navigation, but it appears incremental as it builds on existing methods with novel modules.
The paper tackles the problem of synthesizing ground-level images from aerial images by addressing layout and object representation differences, achieving improved results through enhanced structural alignment and semantic awareness.
Aerial-to-ground image synthesis is an emerging and challenging problem that aims to synthesize a ground image from an aerial image. Due to the highly different layout and object representation between the aerial and ground images, existing approaches usually fail to transfer the components of the aerial scene into the ground scene. In this paper, we propose a novel framework to explore the challenges by imposing enhanced structural alignment and semantic awareness. We introduce a novel semantic-attentive feature transformation module that allows to reconstruct the complex geographic structures by aligning the aerial feature to the ground layout. Furthermore, we propose semantic-aware loss functions by leveraging a pre-trained segmentation network. The network is enforced to synthesize realistic objects across various classes by separately calculating losses for different classes and balancing them. Extensive experiments including comparisons with previous methods and ablation studies show the effectiveness of the proposed framework both qualitatively and quantitatively.