arXiv AI By Haoran Liu, Mingzhe Liu, Peng Li, Guibin Zan

Ranking Image Fusion the Way Humans Do: A Learned Pairwise Preference Measure for Infrared-Visible Fusion Assessment

Read the original on arXiv AI →

arXiv:2608. 01301v3 Announce Type: replace-cross Abstract: Infrared-visible image fusion (IVIF) has no ideal fused reference, so algorithms are ranked by scalar objective metrics that formalize proxies for information transfer, structure, or source similarity.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jul 22

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training

Visible-infrared (VIS-IR) alignment is a key pre-training task for robust multi-sensor perception. Most existing methods use uniform patch-wise contrastive learning, but this can be unreliable in VIS-IR data because imaging-physics differences make some spatially paired regions inherently less comparable, and aligning them with equal strength hinders representation learning and downstream transfer.