TriFlowSR injects low-resolution and reference-image features into a frozen diffusion model through extended attention, adds a Roma-based alignment step, and reports state-of-the-art perceptual RefSR scores including on its new Landmark-4K benchmark.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior
TriFlowSR injects low-resolution and reference-image features into a frozen diffusion model through extended attention, adds a Roma-based alignment step, and reports state-of-the-art perceptual RefSR scores including on its new Landmark-4K benchmark.