整改
图像校正
人工智能
计算机视觉
旋转(数学)
极线几何
失真(音乐)
消失点
计算机科学
运动(物理)
垂直的
点(几何)
运动估计
绕固定轴旋转
计算机立体视觉
立体摄像机
图像稳定
数学
图像(数学)
物理
几何学
放大器
计算机网络
功率(物理)
带宽(计算)
经典力学
量子力学
作者
Yongcong Zhang,Yifei Xue,Ming Liao,Huiqing Zhang,Yizhen Lao
出处
期刊:Cornell University - arXiv
日期:2023-01-01
标识
DOI:10.48550/arxiv.2307.05129
摘要
Despite the increasing prevalence of rotating-style capture (e.g., surveillance cameras), conventional stereo rectification techniques frequently fail due to the rotation-dominant motion and small baseline between views. In this paper, we tackle the challenge of performing stereo rectification for uncalibrated rotating cameras. To that end, we propose Depth-from-Rotation (DfR), a novel image rectification solution that analytically rectifies two images with two-point correspondences and serves for further depth estimation. Specifically, we model the motion of a rotating camera as the camera rotates on a sphere with fixed latitude. The camera's optical axis lies perpendicular to the sphere's surface. We call this latitudinal motion assumption. Then we derive a 2-point analytical solver from directly computing the rectified transformations on the two images. We also present a self-adaptive strategy to reduce the geometric distortion after rectification. Extensive synthetic and real data experiments demonstrate that the proposed method outperforms existing works in effectiveness and efficiency by a significant margin.
科研通智能强力驱动
Strongly Powered by AbleSci AI