Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimation

2026-01-20

AI Summary

Existing open-vocabulary 6D object pose estimation methods rely on global matching, which is prone to interference in cluttered scenes, leading to ambiguous correspondences and degraded accuracy. To address this, this work proposes the FiCoP framework, which replaces global matching with spatially constrained patch-level correspondences. FiCoP introduces a patch-to-patch correlation matrix as a structural prior to restrict the matching scope and incorporates three key components: an object-center decoupling preprocessing step, a Cross-view Global Perception (CPGP) module, and a Patch Correlation Predictor (PCP), collectively enabling fine-grained and noise-robust pose estimation. Evaluated on the REAL275 and Toyota-Light datasets, FiCoP achieves average recall improvements of 8.0% and 6.1%, respectively, significantly outperforming current state-of-the-art methods.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Open-vocabulary 6D object pose estimation empowers robots to manipulate arbitrary unseen objects guided solely by natural language. However, a critical limitation of existing approaches is their reliance on unconstrained global matching strategies. In open-world scenarios, trying to match anchor features against the entire query image space introduces excessive ambiguity, as target features are easily confused with background distractors. To resolve this, we propose Fine-grained Correspondence Pose Estimation (FiCoP), a framework that transitions from noise-prone global matching to spatially-constrained patch-level correspondence. Our core innovation lies in leveraging a patch-to-patch correlation matrix as a structural prior to narrowing the matching scope, effectively filtering out irrelevant clutter to prevent it from degrading pose estimation. Firstly, we introduce an object-centric disentanglement preprocessing to isolate the semantic target from environmental noise. Secondly, a Cross-Perspective Global Perception (CPGP) module is proposed to fuse dual-view features, establishing structural consensus through explicit context reasoning. Finally, we design a Patch Correlation Predictor (PCP) that generates a precise block-wise association map, acting as a spatial filter to enforce fine-grained, noise-resilient matching. Experiments on the REAL275 and Toyota-Light datasets demonstrate that FiCoP improves Average Recall by 8.0% and 6.1%, respectively, compared to the state-of-the-art method, highlighting its capability to deliver robust and generalized perception for robotic agents operating in complex, unconstrained open-world environments. The source code will be made publicly available at https://github.com/zjjqinyu/FiCoP.

Problem

• open-vocabulary
• 6D object pose estimation
• global matching
• background distractors
• spatial ambiguity

Innovation

• fine-grained correspondence
• cross-perspective perception
• open-vocabulary pose estimation
• patch-level matching
• spatial filtering