利用重力方向提升三维重建中相机朝向精度，速度更快且无需全部相机有重力信息。
Gravity-aligned Rotation Averaging with Circular Regression
- 基于圆周回归，将重力方向融入旋转平均，减少自由度
- 在四个大规模数据集上平均提升13 AUC@$1^ ext{°}$，快8倍
- 适用于部分相机有重力信息的场景，适合移动端和无人机应用
从无序图像重建三维场景是计算机视觉与机器人学中的关键任务，广泛应用于众包地图等领域。尽管全局SfM方法具备可扩展性和高效性，但常以牺牲精度为代价。为此，我们提出一种原理性方法，在全局流程的旋转平均阶段引入重力方向，提升相机朝向估计精度并降低自由度。该信息普遍存在于现代智能手机、混合现实设备及无人机中，使本方法易于部署。算法基于圆周回归，具备类似线性回归的收敛性保证，并支持仅部分相机已知重力的情况。此外，我们设计了修正误差重力的机制。在四个大规模数据集上达到当前最优性能：相比SfM基线平均提升13 AUC@$1^ ext{°}$，且运行速度快8倍；优于标准平面位姿图优化23 AUC@$1^ ext{°}$。代码已开源：https://github.com/colmap/glomap。
原文摘要 · Abstract (English)
Reconstructing a 3D scene from unordered images is pivotal in computer vision and robotics, with applications spanning crowd-sourced mapping and beyond. While global Structure-from-Motion (SfM) techniques are scalable and fast, they often compromise on accuracy. To address this, we introduce a principled approach that integrates gravity direction into the rotation averaging phase of global pipelines, enhancing camera orientation accuracy and reducing the degrees of freedom. This additional information is commonly available in recent consumer devices, such as smartphones, mixed-reality devices and drones, making the proposed method readily accessible. Rooted in circular regression, our algorithm has similar convergence guarantees as linear regression. It also supports scenarios where only a subset of cameras have known gravity. Additionally, we propose a mechanism to refine error-prone gravity. We achieve state-of-the-art accuracy on four large-scale datasets. Particularly, the proposed method improves upon the SfM baseline by 13 AUC@$1^\circ$ points, on average, while running eight times faster. It also outperforms the standard planar pose graph optimization technique by 23 AUC@$1^\circ$ points. The code is at https://github.com/colmap/glomap.
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。