A correspondence-based method turns ambiguous 2D-3D matches into a distribution of plausible 6D object poses and outperforms earlier methods on the T-LESS benchmark.
Depth image–based deep learning of grasp planning for textureless planar-faced objects in vision-guided robotic bin-picking,
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
-
Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributions
A correspondence-based method turns ambiguous 2D-3D matches into a distribution of plausible 6D object poses and outperforms earlier methods on the T-LESS benchmark.