SOURCE-LINKED INTELLIGENCE

AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and alleviating projection-induced distortions. However, existing architectures often assume canonical spherical structure and stable viewpoints, which are frequently violated in real-world imagery due to unconstrained camera motion, introducing contextual and geometric ambiguity. Consequently, they lack adaptive mechanisms to handle such ambiguity, limiting robustness to unseen spherical transformations. In contrast, biological perception is inher

Read original source ↗ Open in workspace

recordType

paper

region

Global