FuScore uses MLLMs to output continuous quality scores for IVIF images, constructs per-image soft labels from four sub-dimensions, and applies a tripartite objective with Thurstone fidelity to achieve higher correlation with human preferences than prior metrics.
Bridging human evaluation to infrared and visible image fusion.arXiv preprint arXiv:2603.03871
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.
citing papers explorer
-
Bringing Multimodal Large Language Models to Infrared-Visible Image Fusion Quality Assessment
FuScore uses MLLMs to output continuous quality scores for IVIF images, constructs per-image soft labels from four sub-dimensions, and applies a tripartite objective with Thurstone fidelity to achieve higher correlation with human preferences than prior metrics.
-
Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images
SFRF combines uncertainty-aware multi-scale registration with frequency-domain thermal consistency and dual-branch fusion to handle unregistered infrared-visible image pairs.