OMNI-PoseX: A Fast Vision Model for 6D Object Pose Estimation in Embodied Tasks

TL;DR

OMNI-PoseX is a fast, open-vocabulary vision model that achieves state-of-the-art 6D object pose estimation in real-time, suitable for robotic applications in open-world environments.

Contribution

It introduces a novel architecture that combines open-vocabulary perception with SO(3)-aware pose prediction, improving generalization and stability.

Findings

Achieves SOTA accuracy in 6D pose estimation

Demonstrates real-time performance in robotic grasping

Generalizes well to unseen objects in open-world settings

Abstract

Accurate 6D object pose estimation is a fundamental capability for embodied agents, yet remains highly challenging in open-world environments. Many existing methods often rely on closed-set assumptions or geometry-agnostic regression schemes, limiting their generalization, stability, and real-time applicability in robotic systems. We present OMNI-PoseX, a vision foundation model that introduces a novel network architecture unifying open-vocabulary perception with an SO(3)-aware reflected flow matching pose predictor. The architecture decouples object-level understanding from geometry-consistent rotation inference, and employs a lightweight multi-modal fusion strategy that conditions rotation-sensitive geometric features on compact semantic embeddings, enabling efficient and stable 6D pose estimation. To enhance robustness and generalization, the model is trained on large-scale 6D pose datasets, leveraging broad object diversity, viewpoint variation, and scene complexity to build a scalable open-world pose backbone. Comprehensive evaluations across benchmark pose estimation, ablation studies, zero-shot generalization, and system-level robotic grasping integration demonstrate the effectiveness of OMNI-PoseX. The OMNI-PoseX achieves SOTA pose accuracy and real-time efficiency, while delivering geometrically consistent predictions that enable reliable grasping of diverse, previously unseen objects.