用混合运动基分解相机2D运动，提升复杂场景下的精度与泛化能力。
Estimating 2D Camera Motion with Hybrid Motion Basis
- 融合几何物理基与随机基构建混合运动表示
- 在新基准上零样本测试超越现有方法
- 适合需要高鲁棒性相机运动估计的场景
估计2D相机运动是计算机视觉中的基础任务，旨在建模3D相机运动在2D图像平面上的投影。现有方法或依赖仅适用于平面场景的单应性方法，或使用基于网格的局部单应性（meshflow）技术，难以处理复杂的非线性变换。本文关键洞察是：不同单应性流场的组合会产生单一单应性无法表示的运动模式。我们提出CamFlow框架，通过物理基（源于相机几何）与随机基共同表示相机运动，并设计基于拉普拉斯分布的混合概率损失函数以增强训练鲁棒性。为评估，我们在现有光流数据集上遮蔽动态物体，构建新基准以分离纯相机运动。实验表明，CamFlow在多种场景下均优于当前最优方法，尤其在零样本设置中展现更强鲁棒性与泛化能力。代码与数据集见项目页：https://lhaippp.github.io/CamFlow/。
原文摘要 · Abstract (English)
Estimating 2D camera motion is a fundamental computer vision task that models the projection of 3D camera movements onto the 2D image plane. Current methods rely on either homography-based approaches, limited to planar scenes, or meshflow techniques that use grid-based local homographies but struggle with complex non-linear transformations. A key insight of our work is that combining flow fields from different homographies creates motion patterns that cannot be represented by any single homography. We introduce CamFlow, a novel framework that represents camera motion using hybrid motion bases: physical bases derived from camera geometry and stochastic bases for complex scenarios. Our approach includes a hybrid probabilistic loss function based on the Laplace distribution that enhances training robustness. For evaluation, we create a new benchmark by masking dynamic objects in existing optical flow datasets to isolate pure camera motion. Experiments show CamFlow outperforms state-of-the-art methods across diverse scenarios, demonstrating superior robustness and generalization in zero-shot settings. Code and datasets are available at our project page: https://lhaippp.github.io/CamFlow/.
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。