A spectral dictionary model that reconstructs images as linear combinations of learned sinusoidal bases with a Gaussian prior on coefficients is proposed, but the paper does not provide a workable algorithm or reproducible evidence.
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
REJECT 1representative citing papers
citing papers explorer
-
Spectral Dictionary Learning for Generative Image Modeling
A spectral dictionary model that reconstructs images as linear combinations of learned sinusoidal bases with a Gaussian prior on coefficients is proposed, but the paper does not provide a workable algorithm or reproducible evidence.