DecomPose introduces difficulty-aware gradient decoupling and asymmetric branching to reduce cross-category optimization contention in category-level 6D pose estimation, reporting better results on REAL275, CAMERA25, and HouseCat6D.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
DecomPose introduces difficulty-aware gradient decoupling and asymmetric branching to reduce cross-category optimization contention in category-level 6D pose estimation, reporting better results on REAL275, CAMERA25, and HouseCat6D.