Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4654-4662
DOI: 10.1609/aaai.v40i6.42466 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Lian He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, this task remains challenging due to the need for semantic reasoning and spatial grounding. Existing methods mainly focus on object-level affordances or merely lift 2D predictions to 3D, neglecting rich geometric structure information in point clouds and incurring high computational costs. To address these limitations, we introduce Task-Aware 3D Scene-level Affordance segmentation (TASA), a novel geometry-optimized framework that jointly leverages 2D semantic cues and 3D geometric reasoning in a coarse-to-fine manner. To improve the affordance detection efficiency, TASA features a task-aware 2D affordance detection module to identify manipulable points from language and visual inputs, guiding the selection of task-relevant views. To fully exploit 3D geometric information, a 3D affordance refinement module is proposed to integrate 2D semantic priors with local 3D geometry, resulting in accurate and spatially coherent 3D affordance masks. Experiments on SceneFun3D demonstrate that TASA significantly outperforms the baselines in both accuracy and efficiency in scene-level affordance segmentation.
Zitieren
APA
He, L., Liu, M., Ye, Q., Zhou, Y., Deng, X., & Ding, G. (2026). Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4654-4662. https://doi.org/10.1609/aaai.v40i6.42466
Vancouver
He L, Liu M, Ye Q, Zhou Y, Deng X, Ding G. Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4654-4662. doi:10.1609/aaai.v40i6.42466
BibTeX
@article{He2026,
author = {He, Lian and Liu, Meng and Ye, Qilang and Zhou, Yu and Deng, Xiang and Ding, Gangyi},
title = {Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4654--4662},
doi = {10.1609/aaai.v40i6.42466}
}
EUVIMED