SOURCE-LINKED INTELLIGENCE

PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: prior-free variants regress canonical (NOCS) coordinates directly from local observations and implicitly memorize the canonical frame in the weights, which ties the parameters to category-typical orientations and hurts generalization under distribution shift; prior-based variants introduce a category prior but typically follow a serial deform-then-align pipeline, where underconstrained canonical com

Read original source ↗ Open in workspace

recordType

paper

region

Global