A novel copolymer, poly(N-isopropylacrylamide-co-hydroxypropyl methacrylate-co-3-trimethoxysilypropyl methacrylate) has been synthesized and the hydrodynamic diameters in various aqueous solutions under different temperatures are determined by dynamic light scattering. The results show that the hydrodynamic diameters of copolymers have no obvious change in each working solution below lower critical solution temperature (LCST); across LCST, the diameters increased suddenly at different initial temperature in various aqueous solutions; above LCST, they decreased slightly as the temperature increased in UHQ water, and increased continuously with increasing temperature or salt concentration in saline solutions, and reduced with the rising of pH value in pH buffer. These are attributed to different intermolecular and intramolecular forces leading to disparity in dimension, conformation, and LCST of copolymers. The hydrogen bonding between water molecules and copolymer chains could maintain size and conformation of copolymer single chain; the hydrogen bonding between amide linkages and hydrophobic interactions between isopropyl groups result in intramolecular collapse and intermolecular aggregation; the electrostatic repulsion weakens aggregation extent of copolymers.
Recent learning-based image fusion methods have marked numerous progress in pre-registered multi-modality data, but suffered serious ghosts dealing with misaligned multi-modality data, due to the spatial deformation and the difficulty narrowing cross-modality discrepancy.
To overcome the obstacles, in this paper, we present a robust cross-modality generation-registration paradigm for unsupervised misaligned infrared and visible image fusion (IVIF).
Specifically, we propose a Cross-modality Perceptual Style Transfer Network (CPSTN) to generate a pseudo infrared image taking a visible image as input.
Benefiting from the favorable geometry preservation ability of the CPSTN, the generated pseudo infrared image embraces a sharp structure, which is more conducive to transforming cross-modality image alignment into mono-modality registration coupled with the structure-sensitive of the infrared image.
In this case, we introduce a Multi-level Refinement Registration Network (MRRN) to predict the displacement vector field between distorted and pseudo infrared images and reconstruct registered infrared image under the mono-modality setting.
Moreover, to better fuse the registered infrared images and visible images, we present a feature Interaction Fusion Module (IFM) to adaptively select more meaningful features for fusion in the Dual-path Interaction Fusion Network (DIFN).
Extensive experimental results suggest that the proposed method performs superior capability on misaligned cross-modality image fusion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.