Numerous CNN-based algorithms have been proposed to reconstruct high-quality face images. However, the inability of convolution operation to model long-distance relationships limits the performance of the CNN-based methods. Moreover, in the high-resolution (HR) image reconstruction stage, with the well decoded feature representations, more efficient architecture design can be explored to synthesize pixel-level image details. In this work, we propose a spatial attention-guided CNN-Transformer aggregation network (SCTANet) for face image super-resolution (FSR) tasks. The core component in the deep feature extraction stage is the Hybrid Attention Aggregation (HAA) block. The HAA block has two parallel paths, one for the Residual Spatial Attention (RSA) block, the other for the Multi-scale Patch embedding and Spatial-attention Masked Transformer (MPSMT) block. The HAA block combines the strengths of CNN and transformer to effectively exploit both local and global information. For the reconstruction stage, we propose to use the Sub-pixel MLP-based Upsampling (SMU) module instead of the conventional CNN architecture. The SMU module promotes the reconstruction of pixel-level image details and reduces computational complexity. Extensive experiments on both synthetic and real-world face datasets demonstrate the superiority of our proposed SCTANet over state-of-the-art methods.

Compression artifacts removal methods based on convolutional neural networks have attracted great attention. However, most existing methods require a specific trained model for a specific compression quality factor (QF), which inevitably leads to resource-consuming. Unfortunately, the QF is unknown in most practical applications, so it is intractable to choose a suitable model. In this work, we experimentally analyze the relationship between compression index estimation and compression artifacts removal. Based on the connection between them, we couple compression index estimation with compression artifacts removal into a unified network. A network named CRESNet is proposed, working for a wide range of QFs by integrating channel regulation with an exit strategy. Specifically, CRESNet adopts a multi-stage progressive structure with an exit strategy embedded to automatically select the optimal exit stage according to the estimated compression index reflecting the difficulty of the input sample. Benefiting from the exit strategy, CRESNet removes artifacts from slightly compressed images through a simple process while doing an elaborate process for severely compressed images. Furthermore, a compression-information-guided channel regulation (CICR) mechanism is developed to adaptively regulate feature maps based on the estimated compression index. CRESNet achieves a more elegant trade-off between artifacts removal and detail preservation in a resource-efficient manner. Experiments demonstrate that CRESNet achieves state-of-the-art performance.

For on-orbit radiometric calibration of infrared (IR) satellite instruments, we have developed a blackbody source whose temperature can be accurately determined by use of miniature phase change cells to provide fixed points. The temperatures and reproducibility of six phase change cells containing H2O, Ga–Sn alloy, Ga–Zn alloy, phenyl salicylate (PS), succinonitrile, and Ga were accurately determined by the measurement of the phase change plateaux. The points were measured using the quasiadiabatic vacuum measurement system, which was developed by the National Institute of Metrology, China. The reproducibility time span of the Ga fixed point was as long as six years. Results indicated that the reproducibility values of multiple phase-change run-off point temperatures of H2O, Ga–Sn alloy, Ga–Zn alloy, PS, succinonitrile, and Ga were 2.0, 3.6, 1.5, 3.5, 2.9, and 3.1 mK, respectively. Furthermore, a strong linear relation was observed between the heating power and the run-off temperature. With decreasing heating power, the temperature of the plateau decreased and approached the defined fixed-point value. All simulation results of the miniature fixed points were consistent with the experimental data.