A Geometry-Driven, Framework-Agnostic Optimization for Object Pose Estimation

arXiv:2608.26859v1 Announce Type: new Abstract: Current object pose estimation research remains predominantly model-centric, focusing on architectural innovations and post-processing refinements. This paper introduces a data-centric optimization by proposing a novel, physically grounded rotation representation through principal axes alignment. Our method aligns the object's coordinate system with its inherent geometric axes, derived from inertial properties, yielding three key advantages: Inherent Stability-leveraging the energy-minimizing property of principal axes provides a robust representation that is less sensitive to noise and occlusions; Symmetry-Aware Canonicalization-explicitly resolving rotational ambiguities for symmetric objects at the data level, which fundamentally eliminates label confusion during network training; and Framework Agnosticism-the optimization is applied purely at the dataset level, ensuring plug-and-play compatibility with existing networks without any architectural modification. We validate the framework across diverse category-level and instance-level models. Extensive experiments demonstrate consistent and significant accuracy improvements, while preserving the integrity of the baseline network. This work establishes a new, geometry-driven direction for enhancing pose estimation, circumventing the need for complex network redesign.

Related

• GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation
• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation
• Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement
• Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization
• EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization

Source: arXiv cs.CV | 2026-08-28