Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation
This paper addresses the need for efficient and accurate category-level 6D pose estimation in robotics and augmented reality, offering a real-time solution that outperforms prior methods.
Flow6D introduces a hierarchical flow matching framework for category-level 6D pose estimation that first discretizes pose parameters into bins using discrete flow matching to narrow the search space, then refines with continuous flow matching for accurate residuals, achieving state-of-the-art results on synthetic and real datasets with real-time inference at 70 FPS.
6D pose estimation is a key task in computer vision and embodied AI, widely used in robotic manipulation, augmented reality, etc. Existing methods directly regress in a high-dimensional continuous space, facing two key challenges in category-level pose estimation: limited accuracy due to noise and local optima, and inefficient search over an infinite space that hinders real-time performance. This paper proposes Flow6D, a hierarchical flow matching framework with a two-stage discrete latent space localization-continuous pose regression strategy. Rotation and translation parameters are first discretized into bins, with a discrete flow matching model locking the latent space around the true pose to reduce search complexity. Then, by sampling in the latent space, a continuous flow matching model predicts local pose residuals to optimize the estimate and regress to an accurate pose. The framework also naturally extends to articulated objects, outperforming state-of-the-art methods on synthetic and real datasets with real-time inference at 70 FPS. Project website: https://flow6d.github.io/.