RoboTAG estimates robot poses from monocular images via a topological alignment graph with 2D-3D co-evolution and consistency supervision to alleviate reliance on labeled data.
Llava-uhd v2: an mllm integrating high- resolution feature pyramid via hierarchical window trans- former.arXiv e-prints, pages arXiv–2412
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph
RoboTAG estimates robot poses from monocular images via a topological alignment graph with 2D-3D co-evolution and consistency supervision to alleviate reliance on labeled data.