PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens.
Sebastian StapfTobias BauernfeindMarco RiboldiPublished in: CoRR (2023)
Keyphrases
- confidence level
- prediction intervals
- pose estimation
- computer vision
- human pose
- vision system
- prediction accuracy
- expected cost
- d objects
- human body
- standard deviation
- articulated objects
- fingerprint image quality
- prediction error
- degrees of freedom
- rigid objects
- matching score
- human hand
- body parts
- feature space
- decision trees