Diffusion bridge models and stochastic interpolants enable high-quality image-to-image (I2I) translation by creating paths between distributions in pixel space. However, recent diffusion bridge models excel in image translation but suffer from restricted design flexibility and complicated hyperparameter tuning, whereas Stochastic Interpolants offer greater flexibility but lack essential refinements. We show that these complementary strengths can be unified by interpreting all existing methods within a single SI-based framework. In this work, we unify and expand the space of bridge models by extending Stochastic Interpolants (SIs) with preconditioning, endpoint conditioning, and an optimized sampling algorithm. These enhancements expand the design space of diffusion bridge models, leading to state-of-the-art performance in both image quality and sampling efficiency across diverse I2I tasks. Furthermore, we identify and address a previously overlooked issue of low sample diversity under fixed conditions. We introduce a quantitative analysis for output diversity and demonstrate how we can modify the base distribution for further improvements.

ABSTRACT To enhance the precision of security risk assessment and real‐time control in edge‐based intelligent networks, this article presents a novel risk assessment and control approach leveraging convolutional neural networks (CNNs). This method significantly improves on traditional intelligent network security risk assessment techniques, integrating CNN‐based models to achieve higher accuracy and robustness. By incorporating genetic algorithms and proportional integral derivative control optimization, the proposed approach further ensures stability across intelligent network operations. Using the KDDCup99 network security attack database for evaluation, results demonstrate that this approach achieves a high accuracy rate and low false alarm rate. Additionally, the output signal amplitude closely aligns with the expected amplitude, showing only a 0.02 deviation, while maintaining low evaluation and control times. This ensures comprehensive security across edge intelligent systems, addressing key latency and precision requirements and achieving optimal control effects.

The current popular two-stream two-stage image fusion framework extracts features of infrared and visible images separately and then performs feature fusion. The extracted features lack interaction between the source images and have limited cross-modal complementary capability. To address these issues, we propose a novel one-stream infrared and visible image fusion (OSFusion) framework that connects a source image pair to achieve bidirectional information flow. In this way, the fused features with cross-modal complementary information can be dynamically extracted by mutual guidance. To further improve the inference efficiency and obtain high-quality fused images, a feature extraction and fusion module (FEFM) is proposed based on Transformer structure. The combination of feature extraction and feature fusion is realized by using it. Since there is no need for an extra feature interaction module and the implementation is highly parallel, the speed of image fusion is extremely fast. Benefiting from the one-stream structure and FEFM, OSFusion achieves promising infrared and visible image fusion performance on MSRS, M3FD, and RoadScene datasets. Besides, our method achieves a good balance in the trade-off between performance and complexity, and also shows a faster convergence trend.