Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control

doi:arXiv:2502.03498

	Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
	Ze, Xianghui 1; Song, Zhenbo 1; Wang, Qiwei 2; Lu, Jianfeng 1; Shi, Yujiao2
	2025-02-05
状态	已发表
摘要	Generating street-view images from satellite imagery is a challenging task, particularly in maintaining accurate pose alignment and incorporating diverse environmental conditions. While diffusion models have shown promise in generative tasks, their ability to maintain strict pose alignment throughout the diffusion process is limited. In this paper, we propose a novel Iterative Homography Adjustment (IHA) scheme applied during the denoising process, which effectively addresses pose misalignment and ensures spatial consistency in the generated street-view images. Additionally, currently, available datasets for satellite-to-street-view generation are limited in their diversity of illumination and weather conditions, thereby restricting the generalizability of the generated outputs. To mitigate this, we introduce a text-guided illumination and weather-controlled sampling strategy that enables fine-grained control over the environmental factors. Extensive quantitative and qualitative evaluations demonstrate that our approach significantly improves pose accuracy and enhances the diversity and realism of generated street-view images, setting a new benchmark for satellite-to-street-view generation tasks.
语种	英语
DOI	arXiv:2502.03498
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:121165560
WOS类目	Computer Science, Software Engineering ; Engineering, Electrical& Electronic
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/507025
专题	信息科学与技术学院_PI研究组_师玉娇组
通讯作者	Shi, Yujiao
作者单位	1.Nanjing Univ Sci & Technol, Nanjing, Peoples R China 2.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Ze, Xianghui,Song, Zhenbo,Wang, Qiwei,et al. Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control. 2025.