# Semantic-aware Network for Aerial-to-Ground Image Synthesis

arXiv: https://arxiv.org/abs/2308.06945 · HTML: https://mlsanity.com/paper/2308.06945/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 14 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation](https://mlsanity.com/paper/1904.06807/) (2019)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [Cross-view image synthesis using geometry-guided conditional GANs](https://mlsanity.com/paper/1808.05469/) (2018)
- [Example-Guided Style Consistent Image Synthesis from Semantic Labeling](https://mlsanity.com/paper/1906.01314/) (2019)
- [Image-Based Geo-Localization Using Satellite Imagery](https://mlsanity.com/paper/1903.00159/) (2019)
- [What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1806.05129/) (2018)
- [Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism](https://mlsanity.com/paper/2007.09858/) (2020)
- [Using Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery](https://mlsanity.com/paper/1902.06923/) (2019)
- [Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision](https://mlsanity.com/paper/1911.12362/) (2019)

## Built on by (most cited first, 1 of 1)

- [Skyeyes: Ground Roaming using Aerial View Images](https://mlsanity.com/paper/2409.16685/) (2024)

## Abstract (arXiv)

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.