AI RESEARCH
CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
arXiv CS.AI
•
ArXi:2605.12938v1 Announce Type: cross Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and fisheye lenses. To address this limitation, we propose Curved Ray Expectation Positional Encoding (CRePE