AI RESEARCH

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

arXiv CS.AI

ArXi:2605.15728v1 Announce Type: cross Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible optimization signals in shared modules, resulting in gradient conflicts and negative transfer during