Generative Adversarial Frontal View to Bird View Synthesis

TL;DR

This paper introduces BridgeGAN, a novel generative model that synthesizes bird view images from a single frontal view by using an intermediate homography view, improving accuracy and detail over existing methods.

Contribution

The paper proposes a multi-GAN based model with an intermediate homography view to effectively translate frontal views into bird views, addressing large gap and deformation issues.

Findings

Generated images are more consistent and detailed than existing methods.

Model demonstrates robustness and reliability in challenging cases.

Extensive experiments on synthetic data validate effectiveness.

Abstract

Environment perception is an important task with great practical value and bird view is an essential part for creating panoramas of surrounding environment. Due to the large gap and severe deformation between the frontal view and bird view, generating a bird view image from a single frontal view is challenging. To tackle this problem, we propose the BridgeGAN, i.e., a novel generative model for bird view synthesis. First, an intermediate view, i.e., homography view, is introduced to bridge the large gap. Next, conditioned on the three views (frontal view, homography view and bird view) in our task, a multi-GAN based model is proposed to learn the challenging cross-view translation. Extensive experiments conducted on a synthetic dataset have demonstrated that the images generated by our model are much better than those generated by existing methods, with more consistent global appearance and sharper details. Ablation studies and discussions show its reliability and robustness in some challenging cases.