RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching

Wenzhe Ouyang, Qi Ye, Jinghua Wang, Zenglin Xu, Jiming Chen

Keywords: 6D Pose Estimation, Riemannian Flow Matching, Generative Modeling

Abstract:

We introduce RFMPose, a novel generative framework for category-level 6D object pose estimation that learns deterministic pose trajectories through Riemannian Flow Matching (RFM). Existing discriminative approaches struggle with multi-hypothesis predictions (e.g., symmetry ambiguities) and often require specialized network architectures. RFMPose advances this paradigm through three key innovations:
(1) Ensuring geometric consistency via geodesic interpolation on Riemannian manifolds combined with bi-invariant metric constraints;
(2) Alleviating symmetry-induced ambiguities through Riemannian Optimal Transport for probability mass redistribution without ad-hoc design;
(3) Enabling end-to-end likelihood estimation through Hutchinson trace approximation, thereby eliminating auxiliary model dependencies.
Extensive experiments on the Omni6DPose demonstrate state-of-the-art performance of the proposed method, with significant improvements of $\textbf{+4.1}$ in $\mathrm{\textbf{IoU}_{25}}$ and $\textbf{+2.4}$ in $\textbf{5°2cm}$ metrics compared to prior generative approaches. Furthermore, the proposed RFM framework exhibits robust sim-to-real transfer capabilities and facilitates pose tracking extensions with minimal architectural adaptation.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 20854