Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery

TL;DR

This paper introduces a geometry-guided method for synthesizing realistic street-view panoramas from satellite images by explicitly modeling geometric correspondences, improving the spatial consistency of generated images.

Contribution

It proposes a novel Satellite to Street-view image Projection (S2SP) module that explicitly encodes geometric relations, enhancing cross-view synthesis accuracy.

Findings

Outperforms existing methods on benchmark datasets.

Produces geometrically consistent street-view panoramas.

The S2SP module is differentiable and end-to-end trainable.

Abstract

This paper presents a new approach for synthesizing a novel street-view panorama given an overhead satellite image. Taking a small satellite image patch as input, our method generates a Google's omnidirectional street-view type panorama, as if it is captured from the same geographical location as the center of the satellite patch. Existing works tackle this task as an image generation problem which adopts generative adversarial networks to implicitly learn the cross-view transformations, while ignoring the domain relevance. In this paper, we propose to explicitly establish the geometric correspondences between the two-view images so as to facilitate the cross-view transformation learning. Specifically, we observe that when a 3D point in the real world is visible in both views, there is a deterministic mapping between the projected points in the two-view images given the height information of this 3D point. Motivated by this, we develop a novel Satellite to Street-view image Projection (S2SP) module which explicitly establishes such geometric correspondences and projects the satellite images to the street viewpoint. With these projected satellite images as network input, we next employ a generator to synthesize realistic street-view panoramas that are geometrically consistent with the satellite images. Our S2SP module is differentiable and the whole framework is trained in an end-to-end manner. Extensive experimental results on two cross-view benchmark datasets demonstrate that our method generates images that better respect the scene geometry than existing approaches.