Search papers, labs, and topics across Lattice.
This paper introduces a data-centric optimization approach for object pose estimation that leverages a novel rotation representation based on principal axes alignment. By aligning the object's coordinate system with its geometric axes, the method enhances stability against noise and occlusions, resolves rotational ambiguities for symmetric objects, and maintains compatibility with existing network architectures. Extensive experiments across various models show significant accuracy improvements while preserving baseline network integrity, marking a shift towards geometry-driven methodologies in pose estimation.
Aligning object poses with their geometric axes can dramatically enhance estimation accuracy while simplifying model architecture requirements.
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.
