OneViewAll achieves 92.5% ADD-0.1 accuracy on LINEMOD for novel object 6D pose estimation using only one real reference view by integrating category, symmetry, and patch-level semantic priors in a projection-equivariant alignment.
Freeze: Training-free zero-shot 6d pose estimation with geometric and vision foundation models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MAPRPose reports 76.5% Average Recall on the BOP benchmark for multi-object 6D pose estimation, beating FoundationPose by 3.1% while running 43 times faster through mask-aware proposals and amodal refinement.
citing papers explorer
-
OneViewAll: Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects
OneViewAll achieves 92.5% ADD-0.1 accuracy on LINEMOD for novel object 6D pose estimation using only one real reference view by integrating category, symmetry, and patch-level semantic priors in a projection-equivariant alignment.
-
MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation
MAPRPose reports 76.5% Average Recall on the BOP benchmark for multi-object 6D pose estimation, beating FoundationPose by 3.1% while running 43 times faster through mask-aware proposals and amodal refinement.