A ConvNADE model with Beta output distributions reconstructs color images from partial pixels, and Sobol-based low-discrepancy pixel patches beat random patches in test loss and visual sharpness.
Signal Processing 212, 109158 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Neural Autoregressive Distribution Estimators for Image Reconstruction
A ConvNADE model with Beta output distributions reconstructs color images from partial pixels, and Sobol-based low-discrepancy pixel patches beat random patches in test loss and visual sharpness.