ContactPrompt uses part-wise vertex grids and multi-stage part-conditioned reasoning in MLLMs to achieve training-free dense hand contact estimation that outperforms prior supervised methods.
Keypoint Transformer: Solving joint identification in challenging hands and object interactions for accurate 3D pose estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language Models
ContactPrompt uses part-wise vertex grids and multi-stage part-conditioned reasoning in MLLMs to achieve training-free dense hand contact estimation that outperforms prior supervised methods.