Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.17647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917351581024256 |
|---|---|
| author | Gou, Dongqiang He, Xuming |
| author_facet | Gou, Dongqiang He, Xuming |
| contents | Grounding natural language questions to functionally relevant regions in 3D objects -- termed language-driven 3D affordance grounding -- is essential for embodied intelligence and human-AI interaction. Existing methods, while progressing from label-based to language-driven approaches, still face challenges in open-vocabulary generalization, fine-grained geometric alignment, and part-level semantic consistency. To address these issues, we propose a novel two-stage cross-modal framework that enhances both semantic and geometric representations for open-vocabulary 3D affordance grounding. In the first stage, large language models generate part-aware instructions to recover missing semantics, enabling the model to link semantically similar affordances. In the second stage, we introduce two key components: Affordance Prototype Aggregation (APA), which captures cross-object geometric consistency for each affordance, and Intra-Object Relational Modeling (IORM), which refines geometric differentiation within objects to support precise semantic alignment. We validate the effectiveness of our method through extensive experiments on a newly introduced benchmark, as well as two existing benchmarks, demonstrating superior performance in comparison with existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17647 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment Gou, Dongqiang He, Xuming Computer Vision and Pattern Recognition Grounding natural language questions to functionally relevant regions in 3D objects -- termed language-driven 3D affordance grounding -- is essential for embodied intelligence and human-AI interaction. Existing methods, while progressing from label-based to language-driven approaches, still face challenges in open-vocabulary generalization, fine-grained geometric alignment, and part-level semantic consistency. To address these issues, we propose a novel two-stage cross-modal framework that enhances both semantic and geometric representations for open-vocabulary 3D affordance grounding. In the first stage, large language models generate part-aware instructions to recover missing semantics, enabling the model to link semantically similar affordances. In the second stage, we introduce two key components: Affordance Prototype Aggregation (APA), which captures cross-object geometric consistency for each affordance, and Intra-Object Relational Modeling (IORM), which refines geometric differentiation within objects to support precise semantic alignment. We validate the effectiveness of our method through extensive experiments on a newly introduced benchmark, as well as two existing benchmarks, demonstrating superior performance in comparison with existing methods. |
| title | Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.17647 |