Image fusion synthesizes a new image from multiple images of the same scene. The synthesized image should be suitable for human visual perception and follow-up high-level image-processing tasks. However, existing methods focus on fusing low-level features, ignoring high-level semantic perception information. We propose a new end-to-end model to obtain a more semantically consistent image in infrared and visible image fusion, termed semantic-supervised dual-discriminator generative adversarial network (SDDGAN). In particular, we design an information quantity discrimination (IQD) block to guide fusion progress. For each source image, the block determines the weight for preserving each semantic object's feature. By this way, the generator learns to fuse various semantic objects via different weights to preserve their characteristics. Moreover, the dual discriminator is employed to identify the distribution of infrared and visible information in the fused image. Each discriminator acts on a certain modality (infrared/visible) of different semantic objects in the fused image to preserve and enhance their modality features. Thus, our fused image is more informative. Both the thermal radiation in the infrared image and the visible image texture details can be well preserved. Qualitative and quantitative experiments demonstrate the superiority of our SDDGAN over state-of-the-art methods in terms of visual effects, efficiency, and quantitative metrics.

Treating Idiopathic pulmonary fibrosis (IPF) remains challenging owing to its relentless progression, grim prognosis, and the scarcity of effective treatment options. Emerging evidence strongly supports the critical role of accelerated senescence in alveolar epithelial cells (AECs) in driving the progression of IPF. Consequently, targeting senescent AECs emerges as a promising therapeutic strategy for IPF. Curcumin analogue EF24 is a derivative of curcumin and shows heightened bioactivity encompassing anti-inflammatory, anti-tumor and anti-aging properties. The objective of this study was to elucidate the therapeutic potential and underlying molecular mechanisms of EF24 in the treatment of IPF. A549 and ATII cells were induced to become senescent using bleomycin. Senescence markers were examined using different methods including senescence-associated β-galactosidase (SA-β-gal) staining, western blotting, and q-PCR. Mice were intratracheally administrated with bleomycin to induce pulmonary fibrosis. This was validated by micro-computed tomography (CT), masson trichrome staining, and transmission electron microscope (TEM). The role and underlying mechanisms of EF24 in IPF were determined in vitro and in vivo by evaluating the expressions of PTEN, AKT/mTOR/NF-κB signaling pathway, and mitophagy using western blotting or flow cytometry. We identified that the curcumin analogue EF24 was the most promising candidate among 12 compounds against IPF. EF24 treatment significantly reduced senescence biomarkers in bleomycin-induced senescent AECs, including SA-β-Gal, PAI-1, P21, and the senescence-associated secretory phenotype (SASP). EF24 also effectively inhibited fibroblast activation which was induced by senescent AECs or TGF-β. We revealed that PTEN activation was integral for EF24 to inhibit AECs senescence by suppressing the AKT/mTOR/NF-κB signaling pathway. Additionally, EF24 improved mitochondrial dysfunction through induction of mitophagy. Furthermore, EF24 administration significantly reduced the senescent phenotype induced by bleomycin in the lung tissues of mice. Notably, EF24 mitigates fibrosis and promotes overall health benefits in both the acute and chronic phases of IPF, suggesting its therapeutic potential in IPF treatment. These findings collectively highlight EF24 as a new and effective therapeutic agent against IPF by inhibiting senescence in AECs.

Recently, face hallucination methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e.g., facial parsing maps and landmarks) to focus on global facial structure and constrain facial texture generation. However, the limited receptive fields of CNNs and inaccurate facial priors will reduce the naturalness and fidelity of restored face. In this paper, we propose a FaceFormer that aggregates global representation of Transformers and local representation of CNNs to maintain the consistency of facial structure while restoring local facial details. The reason for this design is that the Transformer can capture global facial information by exploiting the long-distance visual relation modeling, while the local modeling capability of CNNs can recover fine-grained facial details. Therefore, aggregating these two independent representations can help to maximize their merits and reconstruct high-quality and high-fidelity face images. Experimental results of face reconstruction and recognition verify that the proposed FaceFormer significantly outperforms current state-of-the-arts.

Recently, facial priors (e.g., facial parsing maps and facial landmarks) have been widely employed in prior-guided face super-resolution (FSR) because it provides the location of facial components and facial structure information, and helps predict the missing high-frequency (HF) information. However, most existing approaches suffer from two shortcomings: 1) the extracted facial priors are inaccurate since they are extracted from low-resolution (LR) or low-quality super-resolved (SR) face images and 2) they only consider embedding facial priors into the reconstruction process from LR to SR face images, thus failing to explore facial priors to generate LR face image. In this article, we propose a novel pre-prior guided approach that extracts facial prior information from original high-resolution (HR) face images and embeds them into LR ones to obtain HF information-rich LR face images, thereby improving the performance of face reconstruction. Specifically, a novel component hybrid method is proposed, which fuses HR facial components and LR facial background to generate new LR face images (namely, LRmix) via facial parsing maps extracted from HR face images. Furthermore, we design a component hybrid network (CHNet) that learns the LR to LRmix mapping function to ensure that the LRmix can be obtained from LR face images in testing and real-world datasets. Experimental results show that our proposed scheme significantly improves the reconstruction performance for FSR.

Recently, the performances of deep convolution neural networks (CNNs)-based single-image super-resolution (SISR) have been significantly improved. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper networks and ignore the potential relationship between multi-scale features, leading to the limited representation ability of the reconstructed network. To address this problem, we propose a new multi-scale information polymerization network (MIPN). Specifically, we propose a multi-scale information polymerization block (MIPB), which uses convolution layers of different convolution kernel sizes to extract multi-scale image features, and effectively polymerizate the extracted features together to obtain fine image features. Moreover, we also propose a shallow residual block in MIPB. Compared with the traditional convolution layer, this proposed block can effectively extract image features without increasing the number of parameters. Extensive experiments show that the proposed method performs better than several state-of-the-art methods in quantitative and visual quality indicators.

Image alignment/registration/correspondence is a critical prerequisite for many vision-based tasks, and it has been widely studied in computer vision. However, aligning images from different domains, such as cross-weather/season road scenes, remains a challenging problem. Inspired by the success of classic intensity-constancy-based image alignment methods and the modern generative adversarial network (GAN) technology, we propose a cross-weather road scene alignment method called latent generative model with intensity constancy. From a novel perspective, the alignment problem is formulated as a constrained 2D flow optimization problem with latent encoding, which can be decoded into an intensity-constancy image on the latent image manifold. The manifold is parameterized by a pre-trained GAN, which is able to capture statistic characteristics from large datasets. Moreover, we employ the learned manifold to constrain the warped latent image identical to the target image, thereby producing a realistic warping effect. Experimental results on several cross-weather/season road scene datasets demonstrate that our approach can significantly outperform the state-of-the-art methods.