Gaussian of Differences: A Simple and Efficient General Image Fusion Method

Enhanced low-light image fusion through multi-stage processing with Bayesian analysis and quadratic contrast function

This manuscript introduces an innovative multi-stage image fusion framework that adeptly integrates infrared (IR) and visible (VIS) spectrum images to surmount the difficulties posed by low-light settings. The approach commences with an initial preprocessing stage, utilizing an Efficient Guided Image Filter for the infrared (IR) images to amplify edge boundaries and a function for the visible (VIS) images to boost local contrast and brightness. Utilizing a two-scale decomposition technique that incorporates Lipschitz constraints-based smoothing, the images are effectively divided into distinct base and detail layers, thereby guaranteeing the preservation of essential structural information. The process of fusion is carried out in two distinct stages: firstly, a method grounded in Bayesian theory is employed to effectively combine the base layers, so effectively addressing any inherent uncertainty. Secondly, a Surface from Shade (SfS) method is utilized to ensure the preservation of the scene's geometry by enforcing integrability on the detail layers. Ultimately a Choose Max principle is employed to determine the most prominent textural characteristics, resulting in the amalgamation of the base and detail layers to generate an image that exhibits a substantial enhancement in both clarity and detail. The efficacy of our strategy is substantiated by rigorous testing, showcasing notable progressions in edge preservation, detail enhancement, and noise reduction. Consequently, our method presents significant advantages for real-world applications in image analysis.

Infrared and Visual Image Fusion Based on a Local-Extrema-Driven Image Filter

The objective of infrared and visual image fusion is to amalgamate the salient and complementary features of the infrared and visual images into a singular informative image. To accomplish this, we introduce a novel local-extrema-driven image filter designed to effectively smooth images by reconstructing pixel intensities based on their local extrema. This filter is iteratively applied to the input infrared and visual images, extracting multiple scales of bright and dark feature maps from the differences between continuously filtered images. Subsequently, the bright and dark feature maps of the infrared and visual images at each scale are fused using elementwise-maximum and elementwise-minimum strategies, respectively. The two base images, representing the final-scale smoothed images of the infrared and visual images, are fused using a novel structural similarity- and intensity-based strategy. Finally, our fusion image can be straightforwardly produced by combining the fused bright feature map, dark feature map, and base image together. Rigorous experimentation conducted on the widely used TNO dataset underscores the superiority of our method in fusing infrared and visual images. Our approach consistently performs on par or surpasses eleven state-of-the-art image-fusion methods, showcasing compelling results in both qualitative and quantitative assessments.

SharDif: Sharing and Differential Learning for Image Fusion

Image fusion is the generation of an informative image that contains complementary information from the original sensor images, such as texture details and attentional targets. Existing methods have designed a variety of feature extraction algorithms and fusion strategies to achieve image fusion. However, these methods ignore the extraction of common features in the original multi-source images. The point of view proposed in this paper is that image fusion is to retain, as much as possible, the useful shared features and complementary differential features of the original multi-source images. Shared and differential learning methods for infrared and visible light image fusion are proposed. An encoder with shared weights is used to extract shared common features contained in infrared and visible light images, and the other two encoder blocks are used to extract differential features of infrared images and visible light images, respectively. Effective learning of shared and differential features is achieved through weight sharing and loss functions. Then, the fusion of shared features and differential features is achieved via a weighted fusion strategy based on an entropy-weighted attention mechanism. The experimental results demonstrate the effectiveness of the proposed model with its algorithm. Compared with the-state-of-the-art methods, the significant advantage of the proposed method is that it retains the structural information of the original image and has better fusion accuracy and visual perception effect.