← Search

Lu Zou

2 accepted papers

2026

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

ICML 2026poster

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…

Cited by 0SourceScholar