Proposes spherical optimal transport flow matching (SOT-CFM) and spherical flow matching (SFM) for natural image generation by modeling images on a hypersphere based on directional semantic encoding.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometry-Aware Image Flow Matching
Proposes spherical optimal transport flow matching (SOT-CFM) and spherical flow matching (SFM) for natural image generation by modeling images on a hypersphere based on directional semantic encoding.