GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation

2025-02-06

AI Summary

This paper addresses the weak generalization of contextual features in model-agnostic, category-level object pose estimation under partial visibility. We propose a “reconstruct-then-aggregate” paradigm that leverages category-level priors to enhance global semantic-geometric context. Our key contributions are: (1) the Semantic Shape Reconstruction (SSR) module—the first to employ a learnable linear deformation model for category-prototype-guided joint reconstruction from RGB-D inputs; and (2) the Global Context Enhancement (GCE) module, enabling cross-modal fusion of global and local features. The entire framework is end-to-end differentiable, supporting joint geometric and semantic optimization. Evaluated on HouseCat6D and NOCS-REAL275, our method achieves a 12.7% improvement in ADD-S accuracy and demonstrates significantly enhanced robustness under occlusion and truncation.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: State Estimation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

A key challenge in model-free category-level pose estimation is the extraction of contextual object features that generalize across varying instances within a specific category. Recent approaches leverage foundational features to capture semantic and geometry cues from data. However, these approaches fail under partial visibility. We overcome this with a first-complete-then-aggregate strategy for feature extraction utilizing class priors. In this paper, we present GCE-Pose, a method that enhances pose estimation for novel instances by integrating category-level global context prior. GCE-Pose performs semantic shape reconstruction with a proposed Semantic Shape Reconstruction (SSR) module. Given an unseen partial RGB-D object instance, our SSR module reconstructs the instance's global geometry and semantics by deforming category-specific 3D semantic prototypes through a learned deep Linear Shape Model. We further introduce a Global Context Enhanced (GCE) feature fusion module that effectively fuses features from partial RGB-D observations and the reconstructed global context. Extensive experiments validate the impact of our global context prior and the effectiveness of the GCE fusion module, demonstrating that GCE-Pose significantly outperforms existing methods on challenging real-world datasets HouseCat6D and NOCS-REAL275. Our project page is available at https://colin-de.github.io/GCE-Pose/.

Problem

• Enhances pose estimation with global context
• Handles partial visibility in object recognition
• Reconstructs global geometry from partial RGB-D data

Innovation

• Semantic Shape Reconstruction module
• Global Context Enhanced fusion
• Linear Shape Model deformation