AffoGato: Learning Open-Vocabulary Affordance Grounding with Foundation Models

Junha Lee, Eunha Park, Chunghyun Park, Dahyun Kang, Minsu Cho

Keywords: Affordance, Open-Vocabulary, Vision-Language Models, Foundation Models

TL;DR: We introduce AffoGato, an open-vocabulary affordance grounding framework with three stages: automatic generation of Affo-150K, pretraining Gato-3D/2D models on this data, and fine-tuning that demonstrates strong open-vocabulary capabilities.

Abstract: .

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 14674