# Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism

arXiv: https://arxiv.org/abs/2007.09858 · HTML: https://mlsanity.com/paper/2007.09858/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Co-visual pattern augmented generative transformer learning for automobile geo-localization](https://mlsanity.com/paper/2203.09135/) (2022)
- [Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models](https://mlsanity.com/paper/2303.11444/) (2023)
- [Variational Structured Attention Networks for Deep Visual Representation Learning](https://mlsanity.com/paper/2103.03510/) (2021)
- [Semantic-aware Network for Aerial-to-Ground Image Synthesis](https://mlsanity.com/paper/2308.06945/) (2023)
- [HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View](https://mlsanity.com/paper/2311.15478/) (2023)
- [Survey on Controlable Image Synthesis with Deep Learning](https://mlsanity.com/paper/2307.10275/) (2023)

## Abstract (arXiv)

Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or objects are occluded, leading the task very challenging. In this paper, we propose to use Generative Adversarial Networks(GANs) based on a deformable convolution and attention mechanism to solve the problem of cross-view image synthesis (see Fig.1). It is difficult to understand and transform scenes appearance and semantic information from another view, thus we use deformed convolution in the U-net network to improve the network's ability to extract features of objects at different scales. Moreover, to better learn the correspondence between images from different views, we apply an attention mechanism to refine the intermediate feature map thus generating more realistic images. A large number of experiments on different size images on the Dayton dataset[1] show that our model can produce better results than state-of-the-art methods.