Affordance grounding-localizing object regions based on natural language descriptions of interactions-is a critical challenge for enabling intelligent agents to understand and interact with their environments. However, this task remains challenging due to the need for fine-grained part-level localization, the ambiguity arising from multiple valid interaction regions, and the scarcity of large-scale datasets. In this work, we introduce Affogato, a large-scale benchmark comprising 150K instances, annotated with open-vocabulary text descriptions and corresponding 3D affordance heatmaps across a diverse set of objects and interactions. Building on this benchmark, we develop simple yet effective vision-language models that leverage pretrained part-aware vision backbones and a text-conditional heatmap decoder. Our models trained with the Affogato dataset achieve promising performance on the existing 2D and 3D benchmarks, and notably, exhibit effectiveness in open-vocabulary cross-domain generalization. The Affogato dataset is shared in public: https://huggingface.co/datasets/project-affogato/affogato
@article{arxiv.2506.12009,
title = {Affogato: Learning Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale},
author = {Junha Lee and Eunha Park and Chunghyun Park and Dahyun Kang and Minsu Cho},
journal= {arXiv preprint arXiv:2506.12009},
year = {2025}
}