提出仅用旋转表示相机位姿的优化框架，提升三维重建精度与稳定性。
Towards Rotation-only Imaging Geometry: Rotation Estimation
- 将平移参数由旋转推导，实现纯旋转空间下的位姿优化
- 在双视图与多视图场景中均优于当前最优旋转估计方法
- 适合追求高精度三维视觉重建的研究者使用
结构从运动（SfM）是计算机视觉中的关键任务，旨在从一系列二维图像中恢复三维场景结构与相机运动。近期的仅位姿成像几何将三维坐标与相机位姿解耦，通过调整位姿显著提升了SfM性能。延续这一思路，本文探究了场景结构、旋转与平移之间的关键关系，发现平移可由旋转表达，从而将成像几何表示压缩至旋转流形上。为此，本文提出一种基于重投影误差的纯旋转优化框架，适用于双视图与多视图场景。实验结果表明，该方法在准确性和鲁棒性上均优于当前最先进的旋转估计方法，甚至接近多次捆绑调整的结果。期望本工作能推动更精确、高效、可靠的三维视觉计算发展。
原文摘要 · Abstract (English)
Structure from Motion (SfM) is a critical task in computer vision, aiming to recover the 3D scene structure and camera motion from a sequence of 2D images. The recent pose-only imaging geometry decouples 3D coordinates from camera poses and demonstrates significantly better SfM performance through pose adjustment. Continuing the pose-only perspective, this paper explores the critical relationship between the scene structures, rotation and translation. Notably, the translation can be expressed in terms of rotation, allowing us to condense the imaging geometry representation onto the rotation manifold. A rotation-only optimization framework based on reprojection error is proposed for both two-view and multi-view scenarios. The experiment results demonstrate superior accuracy and robustness performance over the current state-of-the-art rotation estimation methods, even comparable to multiple bundle adjustment iteration results. Hopefully, this work contributes to even more accurate, efficient and reliable 3D visual computing.
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。