Interactive residual coordinate attention and contrastive learning for infrared and visible image fusion in triple frequency bands.

The auto-encoder (AE) based image fusion models have achieved encouraging performance on infrared and visible image fusion. However, the meaningful information loss in the encoding stage and simple unlearnable fusion strategy are two significant challenges for such models. To address these issues, this paper proposes an infrared and visible image fusion model based on interactive residual attention fusion strategy and contrastive learning in the frequency domain.

Direct Separation of UO by Coordination Sieve Effect via Spherical Coordination Traps.

Molecule sieve effect (MSE) can enable direct separation of target, thus overcoming two major scientific and industrial separation problems in traditional separation, coadsorption, and desorption. Inspired by this, herein, the concept of coordination sieve effect (CSE) for direct separation of UO , different from the previously established two-step separation method, adsorption plus desorption is reported. The used adsorbent, polyhedron-based hydrogen-bond framework (P-HOF-1), made from a metal-organic framework (MOF) precursor through a two-step postmodification approach, afforded high uptake capacity (close to theoretical value) towards monovalent Cs , divalent Sr , trivalent Eu , and tetravalent Th ions, but completely excluded UO ion, suggesting excellent CSE.