CDNet converts coupled dictionary learning's unique-common prior into a joint unfolding architecture with block-sparse interaction and a high-low frequency fidelity loss, delivering competitive fusion performance at lower compute cost across four image fusion tasks.
Designing CNNs for Multimodal Image Restoration and Fusion via Unfolding the Method of Multipliers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion
CDNet converts coupled dictionary learning's unique-common prior into a joint unfolding architecture with block-sparse interaction and a high-low frequency fidelity loss, delivering competitive fusion performance at lower compute cost across four image fusion tasks.