Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.
Figures & tables
Figure 1: Overview of our work. Left: We introduce PAP-12K, the first large-scale benchmark dedicated to panoramic affordance prediction, featuring ultra-high resolution (12K) imagery, rich reasoning-based QA pairs, and explicitly capturing unique panoramic challenges (geometric distortion, boundary discontinuity, and extreme scale variations). Right: We propose the PAP framework, which mimics human foveal vision to tackle these challenges. It employs Recursive Visual Routing for efficient coarse localization, an Adaptive Gaze mechanism to rectify spatial distortions, and Cascaded Affordance Grounding for precise instance-level mask extraction.
Table 1: Comparison of our proposed PAP-12K with existing affordance and panoramic datasets. Some Dataset has various resolutions, we adopt the largest resolution for comparison.
School of Artificial Intelligence and Robotics, Hunan University, Changsha 410012, China · National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha 410082, China