ASASR recasts generative super-resolution flow into Sobolev Riemannian geometry via spectrally colored noise kernels and parametric adversaries from the Riesz Representation Theorem to enforce structural fidelity.
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
-
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
ASASR recasts generative super-resolution flow into Sobolev Riemannian geometry via spectrally colored noise kernels and parametric adversaries from the Riesz Representation Theorem to enforce structural fidelity.