ThinkAfford decomposes 3D affordance grounding into high-recall proposal generation and GRPO-trained vision-language selection, reporting state-of-the-art AP25 on SceneFun3D.
Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes
ThinkAfford decomposes 3D affordance grounding into high-recall proposal generation and GRPO-trained vision-language selection, reporting state-of-the-art AP25 on SceneFun3D.