Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Views

TL;DR

This paper introduces a novel pipeline for generating high-resolution, geospecific ground views from satellite images, leveraging a building refinement method and a geospecific prior to produce realistic urban ground images.

Contribution

It presents a new approach that directly predicts ground views from satellite data, incorporating a building refinement technique and a geospecific prior for improved accuracy.

Findings

Achieves a tenfold increase in ground view resolution.

Produces realistic, geospecific ground images from satellite data.

First method to generate close-to-real ground views solely from satellite images.

Abstract

Predicting realistic ground views from satellite imagery in urban scenes is a challenging task due to the significant view gaps between satellite and ground-view images. We propose a novel pipeline to tackle this challenge, by generating geospecifc views that maximally respect the weak geometry and texture from multi-view satellite images. Different from existing approaches that hallucinate images from cues such as partial semantics or geometry from overhead satellite images, our method directly predicts ground-view images at geolocation by using a comprehensive set of information from the satellite image, resulting in ground-level images with a resolution boost at a factor of ten or more. We leverage a novel building refinement method to reduce geometric distortions in satellite data at ground level, which ensures the creation of accurate conditions for view synthesis using diffusion networks. Moreover, we proposed a novel geospecific prior, which prompts distribution learning of diffusion models to respect image samples that are closer to the geolocation of the predicted images. We demonstrate our pipeline is the first to generate close-to-real and geospecific ground views merely based on satellite images.