Skyeyes: Ground Roaming using Aerial View Images

TL;DR

Skyeyes is a novel framework that generates photorealistic ground view images from aerial images, improving scene realism and coherence for applications like autonomous driving and gaming.

Contribution

It introduces a new method combining 3D representation with view consistent generation, and provides a synthetic geo-aligned dataset for ground and aerial imagery.

Findings

Outperforms existing synthesis methods in quality and realism.

Ensures geometric and temporal coherence in generated images.

Creates a large synthetic dataset for aerial-ground image pairs.

Abstract

Integrating aerial imagery-based scene generation into applications like autonomous driving and gaming enhances realism in 3D environments, but challenges remain in creating detailed content for occluded areas and ensuring real-time, consistent rendering. In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience. More specifically, we combine a 3D representation with a view consistent generation model, which ensures coherence between generated images. This method allows for the creation of geometrically consistent ground view images, even with large view gaps. The images maintain improved spatial-temporal coherence and realism, enhancing scene comprehension and visualization from aerial perspectives. To the best of our knowledge, there are no publicly available datasets that contain pairwise geo-aligned aerial and ground view imagery. Therefore, we build a large, synthetic, and geo-aligned dataset using Unreal Engine. Both qualitative and quantitative analyses on this synthetic dataset display superior results compared to other leading synthesis approaches. See the project page for more results: https://chaoren2357.github.io/website-skyeyes/.