Diff9D is a diffusion-based category-level 9-DoF pose estimator that trains only on synthetic data and reports state-of-the-art domain generalization on REAL275, Wild6D, and robotic grasping.
Epro- pnp: Generalized end-to-end probabilistic perspective-n-points for monocular object pose estimation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation
Diff9D is a diffusion-based category-level 9-DoF pose estimator that trains only on synthetic data and reports state-of-the-art domain generalization on REAL275, Wild6D, and robotic grasping.