RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimation
This work addresses efficiency bottlenecks in pose estimation for applications like virtual reality and embodied intelligence, though it builds incrementally on existing generative models.
The paper tackles the problem of slow category-level 6D object pose estimation by proposing RFM-Pose, which uses flow-matching and reinforcement learning to accelerate pose generation and refine hypotheses, achieving favorable performance on the REAL275 benchmark with reduced computational cost.
Object pose estimation is a fundamental problem in computer vision and plays a critical role in virtual reality and embodied intelligence, where agents must understand and interact with objects in 3D space. Recently, score based generative models have to some extent solved the rotational symmetry ambiguity problem in category level pose estimation, but their efficiency remains limited by the high sampling cost of score-based diffusion. In this work, we propose a new framework, RFM-Pose, that accelerates category-level 6D object pose generation while actively evaluating sampled hypotheses. To improve sampling efficiency, we adopt a flow-matching generative model and generate pose candidates along an optimal transport path from a simple prior to the pose distribution. To further refine these candidates, we cast the flow-matching sampling process as a Markov decision process and apply proximal policy optimization to fine-tune the sampling policy. In particular, we interpret the flow field as a learnable policy and map an estimator to a value network, enabling joint optimization of pose generation and hypothesis scoring within a reinforcement learning framework. Experiments on the REAL275 benchmark demonstrate that RFM-Pose achieves favorable performance while significantly reducing computational cost. Moreover, similar to prior work, our approach can be readily adapted to object pose tracking and attains competitive results in this setting.