Yu Fu

Yu Fu, TianYang Xu, XiaoJun Wu et al.

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the Vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection.These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues.Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network.

Yu Fu, Xiao-Jun Wu, Josef Kittler

Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied to many image processing tasks. In this paper, we apply the image decomposition network to the image fusion task. We input infrared image and visible light image and decompose them into three high-frequency feature images and a low-frequency feature image respectively. The two sets of feature images are fused using a specific fusion strategy to obtain fusion feature images. Finally, the feature images are reconstructed to obtain the fused image. Compared with the state-of-the-art fusion methods, this method has achieved better performance in both subjective and objective evaluation.

Yu Fu, Xiao-Jun Wu

Deep learning is a rapidly developing approach in the field of infrared and visible image fusion. In this context, the use of dense blocks in deep networks significantly improves the utilization of shallow information, and the combination of the Generative Adversarial Network (GAN) also improves the fusion performance of two source images. We propose a new method based on dense blocks and GANs , and we directly insert the input image-visible light image in each layer of the entire network. We use SSIM and gradient loss functions that are more consistent with perception instead of mean square error loss. After the adversarial training between the generator and the discriminator, we show that a trained end-to-end fusion network -- the generator network -- is finally obtained. Our experiments show that the fused images obtained by our approach achieve good score based on multiple evaluation indicators. Further, our fused images have better visual effects in multiple sets of contrasts, which are more satisfying to human visual perception.