用生成模型估算相机位姿，自动给出不确定性，更可靠。
PoseFM: Relative Camera Pose Estimation Through Flow Matching
- 将单目位姿估计转为生成任务，通过连续时间微分方程建模运动分布。
- 在TartanAir、KITTI等数据集上达到最低绝对轨迹误差，性能领先。
- 适合需要可靠运动估计的自动驾驶、AR等场景，尤其视觉条件差时。
单目视觉里程计是自动驾驶、增强现实等应用中的基础计算机视觉问题。尽管基于深度学习的方法在结构或光照不佳环境下已超越传统几何方法，但多数依赖确定性回归，缺乏对不确定性的感知。本文提出PoseFM，首个将单目帧间里程计重构为生成任务的框架，采用流匹配（Flow Matching, FM）建模相机运动为分布而非点估计，通过连续时间常微分方程从噪声生成真实位姿。该方法提供了一种可解释的不确定性估计机制，在复杂视觉条件下仍能实现鲁棒运动推断。在TartanAir、KITTI和TUM-RGBD基准上的评估显示，PoseFM在部分轨迹上取得最低绝对轨迹误差（ATE），整体性能与当前最佳单目帧间里程计方法相当。代码与模型检查点将公开于https://github.com/helsinki-sda-group/posefm。
原文摘要 · Abstract (English)
Monocular visual odometry (VO) is a fundamental computer vision problem with applications in autonomous navigation, augmented reality and more. While deep learning-based methods have recently shown superior accuracy compared to traditional geometric pipelines, particularly in environments where handcrafted features struggle due to poor structure or lighting conditions, most rely on deterministic regression, which lacks the uncertainty awareness required for robust applications. We propose PoseFM, the first framework to reformulate monocular frame-to-frame VO as a generative task using Flow Matching (FM). By leveraging FM, we model camera motion as a distribution rather than a point estimate, learning to transform noise into realistic pose predictions via continuous-time ODEs. This approach provides a principled mechanism for uncertainty estimation and enables robust motion inference under challenging visual conditions. In our evaluations, PoseFM achieves strong performance on TartanAir, KITTI and TUM-RGBD benchmarks, achieving the lowest absolute trajectory error (ATE) on some of the trajectories and overall being competitive with the best frame-to-frame monocular VO methods. Code and model checkpoints will be made available at https://github.com/helsinki-sda-group/posefm.
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。