破解滚动快门单视图三维重建难题，揭示可恢复的运动与场景参数。
Single-View Rolling-Shutter SfM
- 基于滚动快门几何特性建模单图像点/线空间关系
- 证明从单张图像可恢复部分运动与场景参数
- 为实际应用提供可行解法与限制分析
滚动快门（RS）相机无处不在，但单视图滚动快门结构重建（RS SfM）仍未完全解决。本文提出一种新方法：刻画观测世界点或线在滚动快门单视图下的几何特性。利用该几何模型，系统分析哪些运动和场景参数可从单张RS图像中恢复，并推导出最小化重建问题。通过多个典型案例的验证，设计了概念验证求解器，既展示了可行性，也揭示了实际应用中的局限性。
原文摘要 · Abstract (English)
Rolling-shutter (RS) cameras are ubiquitous, but RS SfM (structure-from-motion) has not been fully solved yet. This work suggests an approach to remedy this: We characterize RS single-view geometry of observed world points or lines. Exploiting this geometry, we describe which motion and scene parameters can be recovered from a single RS image and systematically derive minimal reconstruction problems. We evaluate several representative cases with proof-of-concept solvers, highlighting both feasibility and practical limitations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。