RoboPEPP pre-trains a vision encoder to predict masked robot joints from context, improving pose and joint angle accuracy and occlusion robustness over prior work on the DREAM benchmark.
Asano, Christian Rupprecht, and Andrea Vedaldi
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
RoboPEPP pre-trains a vision encoder to predict masked robot joints from context, improving pose and joint angle accuracy and occlusion robustness over prior work on the DREAM benchmark.