PoseFM Flow-Based Camera Pose Estimation Framework
Figure 1: Overview of the PoseFM framework. (a) PoseFM Pipeline : The pipeline consists of an optical flow estimator f ϕ f_{\phi} and parametrized vector field network. The output of the pipeline is a point estimate of the vector field u ^ τ \hat{u}_{\tau} . (b) Inference Procedure : Given an image pair ( I t , I t + 1 ) (I_{t},I_{t+1}) , we sample a pose X 0 X_{0} from the initial distribution and numerically integrate the learned vector field using an ODE solver to recover the final camera motion. (c) Model Architecture : A detailed view of the network parameterizing u τ u_{\tau} .
논문 컨텍스트
Paper title: PoseFM: Relative Camera Pose Estimation Through Flow Matching Abstract: 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. Passages referencing this figure: rmance 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. K eywords Computer Vision ⋅ \cdot Visual Odometry ⋅ \cdot Flow Matching 1 Introduction Figure 1: Overview of the PoseFM framework. (a) PoseFM Pipeline : The pipeline consists of an optical flow estimator f ϕ f_{\phi} and parametrized vector field network. The output of the pipeline is a point estimate of the vector field u ^ τ \hat{u}_{\tau} . (b) Inference Procedure : Given an image pair ( I t , I t + 1 ) (I_{t},I_{t+1}) , we sample a pose X 0 X_{0} from the initial distribution an
