AI RESEARCH
Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera
arXiv CS.CV
•
ArXi:2511.18174v2 Announce Type: replace Modern perception increasingly relies on fisheye, panoramic, and other wide field-of-view (FoV) cameras, yet most pipelines still apply planar CNNs designed for pinhole imagery on 2D grids, where pixel-space neighborhoods misrepresent physical adjacency and models are sensitive to global rotations. Traditional spherical CNNs partially address this mismatch but require costly spherical harmonic transform that constrains resolution and efficiency.