AI RESEARCH
FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception
arXiv CS.AI
•
ArXi:2604.10391v1 Announce Type: cross Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial representations assume the rectilinear geometry of pinhole cameras. Fisheye cameras, widely deployed on production autonomous vehicles for their surround-view coverage, exhibit severe radial distortion that renders these representations geometrically inconsistent. At the same time, the scarcity of large-scale fisheye annotations makes re.