Meta-Learning-Based Degradation Representation for Blind Super-Resolution.

Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e. g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various degradation processes.

Computer assisted system for precise lung surgery based on medical image computing and mixed reality.

The key of a surgical treatment for the lung cancer is to remove the infected part with the least excision and to retain most of the healthy lung tissue. The traditional computer surgery assisted system show that the patient's CT images or three-dimensional structure in the PC screen. This assisted system is not a real three-dimensional system and can't display well the position of pulmonary vessels and trachea of the patients to surgeon. To solve the problem, a computer assisted system for precise lung surgery for precise surgery based on medical image and VR is developed in this paper. Firstly, the regional growth and filling algorithm is designed to segment lung trachea and lung vessels. Then, the reference edge grid algorithm is used to construct the model of the segmentation trachea and lung vessels. And the models are saved as an identifiable STL type file. Finally, according to the system analysis for the specific system function, the computer assisted system is implemented to display the three-dimensional pulmonary vessels and trachea on the mixed reality device. The surgeons can observe and interface precisely the real three-dimensional lung structure of the patient to help them operate accurately the lung surgery.