RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization
Open paper
Benchmark
Model
Rank
Results
6d-pose-estimation-on-linemod
RNNPose
#1
Mean ADD: 97.37
Accuracy (ADD): 97.37%
6d-pose-estimation-using-rgb-on-occlusion
RNNPose (Trained with synthetic data and LINEMOD training set, w/o pbr data)
#2
Mean ADD: 60.65
Rank counts only results with a code link.