ZeroKey detects 3D keypoints on unseen object categories by prompting the Molmo vision-language model on multiple rendered views and aggregating the back-projected points, with no 3D annotations required.
Claude 3.5 sonnet model card addendum
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models
ZeroKey detects 3D keypoints on unseen object categories by prompting the Molmo vision-language model on multiple rendered views and aggregating the back-projected points, with no 3D annotations required.