Skip to main content
Search

# Rotary Position Encoding

1 related articles

Subscribe to updates
  1. arXiv

    RouTex turns rotary position encoding into a reference router, filling in unseen 3D surfaces and reaching FID 12.06

    A single reference image shows only one side of an object, so back-side texture must be guessed from priors and often invents details. RouTex rewrites 3D rotary position encoding inside a 2D multi-view diffusion framework into explicit reference-to-view correspondence without adding parameters, and pairs it with dual-granularity attention for local texture and cross-view consistency. On a 475-asset evaluation set conditioned on four orthographic views it reaches FID 12.06, below TRELLIS at 18.83 and TRELLIS.2 at 12.93.

You’re all caught up