The field of image and signal restoration is rapidly advancing, driven by innovative applications of deep learning and other techniques. Recent developments have focused on improving the resolution and quality of images and videos, particularly in challenging environments such as low-light conditions or in the presence of noise and haze. Researchers are also exploring new methods for inspecting and analyzing infrastructure, such as roads and bridges, using high-performance imaging and advanced AI analytics. Furthermore, there is a growing interest in developing more accurate and efficient methods for estimating propagation factors in various environments, which is crucial for effective deployment of radar technologies. Noteworthy papers in this area include the proposal of a self-supervised ultrasound video super-resolution algorithm, which outperforms existing methods and has significant implications for clinical practice. Another notable work is the introduction of a visual transformer framework for ultra-high-definition image dehazing, which achieves state-of-the-art performance while reducing computational requirements. Additionally, the development of a multimodal framework for 3D CT radiology question answering has shown promising results in addressing the complexities of anatomical relationships and spatial dependencies in medical imaging.