GREAT combines multimodal language model reasoning with 3D geometry to ground open-vocabulary object affordances, and introduces the large PIADv2 dataset.
3d affordancenet: A benchmark for visual object affordance understanding
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
-
GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding
GREAT combines multimodal language model reasoning with 3D geometry to ground open-vocabulary object affordances, and introduces the large PIADv2 dataset.