RelWitness introduces relation witnesses from visual and geometric cues to learn open-vocabulary 3D scene graphs under incomplete supervision using a positive-unlabeled objective.
Title resolution pending
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
-
RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses
RelWitness introduces relation witnesses from visual and geometric cues to learn open-vocabulary 3D scene graphs under incomplete supervision using a positive-unlabeled objective.