PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918381538508800 |
|---|---|
| author | Zhu, Guoliang Jia, Wanjun Shao, Caoyang Zhang, Yuheng Li, Zhiyong Yang, Kailun |
| author_facet | Zhu, Guoliang Jia, Wanjun Shao, Caoyang Zhang, Yuheng Li, Zhiyong Yang, Kailun |
| contents | Global perception is essential for embodied agents in 360° spaces, yet current affordance grounding remains largely object-centric and restricted to perspective views. To bridge this gap, we introduce a novel task: Holistic Affordance Grounding in 360° Indoor Environments. This task faces unique challenges, including severe geometric distortions from Equirectangular Projection (ERP), semantic dispersion, and cross-scale alignment difficulties. We propose PanoAffordanceNet, an end-to-end framework featuring a Distortion-Aware Spectral Modulator (DASM) for latitude-dependent calibration and an Omni-Spherical Densification Head (OSDH) to restore topological continuity from sparse activations. By integrating multi-level constraints comprising pixel-wise, distributional, and region-text contrastive objectives, our framework effectively suppresses semantic drift under low supervision. Furthermore, we construct 360-AGD, the first high-quality panoramic affordance grounding dataset. Extensive experiments demonstrate that PanoAffordanceNet significantly outperforms existing methods, establishing a solid baseline for scene-level perception in embodied intelligence. The source code and benchmark dataset will be made publicly available at https://github.com/GL-ZHU925/PanoAffordanceNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09760 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments Zhu, Guoliang Jia, Wanjun Shao, Caoyang Zhang, Yuheng Li, Zhiyong Yang, Kailun Computer Vision and Pattern Recognition Robotics Image and Video Processing Global perception is essential for embodied agents in 360° spaces, yet current affordance grounding remains largely object-centric and restricted to perspective views. To bridge this gap, we introduce a novel task: Holistic Affordance Grounding in 360° Indoor Environments. This task faces unique challenges, including severe geometric distortions from Equirectangular Projection (ERP), semantic dispersion, and cross-scale alignment difficulties. We propose PanoAffordanceNet, an end-to-end framework featuring a Distortion-Aware Spectral Modulator (DASM) for latitude-dependent calibration and an Omni-Spherical Densification Head (OSDH) to restore topological continuity from sparse activations. By integrating multi-level constraints comprising pixel-wise, distributional, and region-text contrastive objectives, our framework effectively suppresses semantic drift under low supervision. Furthermore, we construct 360-AGD, the first high-quality panoramic affordance grounding dataset. Extensive experiments demonstrate that PanoAffordanceNet significantly outperforms existing methods, establishing a solid baseline for scene-level perception in embodied intelligence. The source code and benchmark dataset will be made publicly available at https://github.com/GL-ZHU925/PanoAffordanceNet. |
| title | PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor Environments |
| topic | Computer Vision and Pattern Recognition Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2603.09760 |