SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ze, Xianghui, Zhu, Beiyi, Song, Zhenbo, Lu, Jianfeng, Shi, Yujiao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915545189711872
author Ze, Xianghui
Zhu, Beiyi
Song, Zhenbo
Lu, Jianfeng
Shi, Yujiao
author_facet Ze, Xianghui
Zhu, Beiyi
Song, Zhenbo
Lu, Jianfeng
Shi, Yujiao
contents Generating multiview-consistent $360^\circ$ ground-level scenes from satellite imagery is a challenging task with broad applications in simulation, autonomous navigation, and digital twin cities. Existing approaches primarily focus on synthesizing individual ground-view panoramas, often relying on auxiliary inputs like height maps or handcrafted projections, and struggle to produce multiview consistent sequences. In this paper, we propose SatDreamer360, a framework that generates geometrically consistent multi-view ground-level panoramas from a single satellite image, given a predefined pose trajectory. To address the large viewpoint discrepancy between ground and satellite images, we adopt a triplane representation to encode scene features and design a ray-based pixel attention mechanism that retrieves view-specific features from the triplane. To maintain multi-frame consistency, we introduce a panoramic epipolar-constrained attention module that aligns features across frames based on known relative poses. To support the evaluation, we introduce {VIGOR++}, a large-scale dataset for generating multi-view ground panoramas from a satellite image, by augmenting the original VIGOR dataset with more ground-view images and their pose annotations. Experiments show that SatDreamer360 outperforms existing methods in both satellite-to-ground alignment and multiview consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00600
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
Ze, Xianghui
Zhu, Beiyi
Song, Zhenbo
Lu, Jianfeng
Shi, Yujiao
Computer Vision and Pattern Recognition
Generating multiview-consistent $360^\circ$ ground-level scenes from satellite imagery is a challenging task with broad applications in simulation, autonomous navigation, and digital twin cities. Existing approaches primarily focus on synthesizing individual ground-view panoramas, often relying on auxiliary inputs like height maps or handcrafted projections, and struggle to produce multiview consistent sequences. In this paper, we propose SatDreamer360, a framework that generates geometrically consistent multi-view ground-level panoramas from a single satellite image, given a predefined pose trajectory. To address the large viewpoint discrepancy between ground and satellite images, we adopt a triplane representation to encode scene features and design a ray-based pixel attention mechanism that retrieves view-specific features from the triplane. To maintain multi-frame consistency, we introduce a panoramic epipolar-constrained attention module that aligns features across frames based on known relative poses. To support the evaluation, we introduce {VIGOR++}, a large-scale dataset for generating multi-view ground panoramas from a satellite image, by augmenting the original VIGOR dataset with more ground-view images and their pose annotations. Experiments show that SatDreamer360 outperforms existing methods in both satellite-to-ground alignment and multiview consistency.
title SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.00600