A VAE trained to imitate DINO-SAM2 generated masks and keypoint heatmaps localizes weld pool keypoints with 13.4 pixel mean error, without manual labels for training.
Title resolution pending
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
-
Leveraging Foundation Models To learn the shape of semi-fluid deformable objects
A VAE trained to imitate DINO-SAM2 generated masks and keypoint heatmaps localizes weld pool keypoints with 13.4 pixel mean error, without manual labels for training.