A new 1,369-pair visible-infrared campus dataset and a three-part evaluation framework show that general fusion metrics do not predict zero-shot pedestrian detection accuracy.
Sedrfuse: A symmetric encoder–decoder with residual block network for infrared and visible image fusion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Design and Evaluation of Deep Learning-Based Dual-Spectrum Image Fusion Methods
A new 1,369-pair visible-infrared campus dataset and a three-part evaluation framework show that general fusion metrics do not predict zero-shot pedestrian detection accuracy.