The field of face sketch-to-photo synthesis involves generating photographic facial images with enhanced details and a heightened sense of style realism. In recent years, the advancement of deep learning techniques has significantly contributed to the development of methods for synthesizing photographic face images from sketches. Nevertheless, challenges remain in synthesizing facial photographs with richer details and more accurate structural representation. This paper introduces a novel architecture for face sketch-to-photo synthesis, using denoising diffusion probabilistic models (DDPM). Our approach simplifies the complex transformation process into sequential forward and backward denoising steps. We incorporate a pretrained coarse generator to effectively encode sketch information, integrating it into each backward step to guide the generative process toward accurate photo space representation. Furthermore, we design a detail diffusion branch to refine the coarse photo face generated from the coarse generator. By deeply fusing multiscale detail features from this branch with a sophisticated conditional noise predictor, our model effectively captures the correlation between detail and stylistic elements both in sketches and in photographic faces. Extensive experimental evaluations on three datasets show the effectiveness of our model, emphasizing its ability to synthesize facial photographs with remarkable realism and rich detail. The synthesized facial images consistently demonstrate superior face recognition accuracy, surpassing that of state-of-the-art methods.

Small object detection remains a bottleneck because there is little visual information about them, especially in the deep layers. To improve the detection performance of small objects, here, Swin Transformer is introduced as the model backbone network to extract rich features of small objects. Then, a multilevel receptive field expansion network (MRFENet) is proposed based on the characteristics of different stages in the Swin Transformer. Specifically, a receptive field expansion block (RFEB) is designed to acquire contextual cues and extract detailed information. The RFEB is carefully designed to target the required receptive fields of different layers and further refine the features. MRFENet combined with RFEBs implements the retention of small object context cues and the acquisition of receptive fields for the adaptive detection tasks. Finally, a union loss function is designed to enhance the localization ability. Experiments on the MS COCO dataset demonstrate that the proposed MRFENet has a significant improvement against other state‐of‐the‐art methods, which further validates that MRFENet can effectively utilize small object information.

A dual-band and ±45 • dual-polarized antenna is proposed for 2G/3G mobile communications in this paper. The proposed antenna consists of five elements for the lower band and ten elements for the upper band. Results for a single element and antenna array are presented. The front-to-back ratio is from 25 dB to 30 dB, and the axial cross polarization ratio is from 19 dB to 22 dB in a single low band unit. The dual-band array achieves a bandwidth of 15.7% (820-960 MHz) for the lower band and a bandwidth of 23.7% (1710-2170 MHz) for the upper band, covering the frequency bands required by 2G/3G systems. Simulation results show that the gains for antenna array are 15.7 dBi for the lower band and 19.1 dBi for the upper band, which is suitable for base stations applications.

The rapid development of remote‐sensing data acquisition technology means that the resolution of remote‐sensing image has been continuously improved, resulting in the large scale of remote‐sensing image data and the increase of redundant information, which restricts the image processing and analysis. However, super‐pixel segmentation method mainly aimed at the general image segmentation algorithm, rarely for remote‐sensing image. Therefore, here, the polarisation decomposition of full‐polarised remote‐sensing images is used to synthesise pseudo‐colour images. Then, based on the region, the image segmentation algorithm based on the colour feature of SLIC super‐pixel segmentation algorithm is used to make it have important application value in remote‐sensing image target extraction. Here, the image of Danjiangkou reservoir obtained by high‐resolution space‐borne SAR is selected as the research object. Finally, the polarisation decomposition and segmentation of full‐polarised remote‐sensing images are realised, and the advantages of SLIC super‐pixel algorithm are proved.