The single-image super-resolution (SISR) network based on deep learning is dedicated to learning the mapping between low-resolution (LR) images and high-resolution (HR) images. The optimal parameters of these networks often require extensive training on large-scale external image databases. For medical magnetic resonance (MR) images, there is a lack of large data sets containing high-quality images. Some deep networks that perform well on natural images cannot be fully trained on MR images, which limits the super-resolution (SR) performance. In traditional methods, the non-local self-similarity has been verified as useful statistical prior information for image restoration. The inherent feature correlation not only exists between pixels, but some patches also tend to be repeated at different positions within and across scales of MR images. Therefore, in this paper, we propose a mixed self-similarity attention network (MSAN) to explore the long-range dependencies of different regions fully. In the feature map of the entire input MR image, the prior information of self-similarity is divided into two scales: point-similarity and patch-similarity. We use points and patches that are highly similar to the current area to restore a more detailed structural texture. The internal correlation items can be used as an essential supplement to the limited external training dataset. Besides, the large number of less informative background in MR images will interfere with practical self-similarity information. A dual attention mechanism combining first-order attention and second-order attention gives more weight to salient features and suppresses the activation of useless features. Comprehensive experiments demonstrate that the proposed achieves significantly superior results on MR images SR while outperforming state-of-the-art methods by a large margin quantitatively and visually.
In the current popular visual tasks, one single model is usually used to output the final results. But no model is perfect, in this paper, we propose a simple and general multi-model method. To combine the advantages of multiple models, we design a familiarity prediction network to output the model's familiarity of images, then select the optimal model based on the familiarity value. Since the loss value is a single value, the familiarity value of any task can be reflected in the loss value, so the output of the familiarity prediction network can be regarded as an estimate of the loss value. The accuracy of the multi-model exceeds any single model that composes the multi-model. By limiting the number of feature layers input into the familiarity network, the sacrifice of computation and detection speed is acceptable. Our method is general and task-agnostic, it not only performs well on classification tasks but also on object detection tasks and other vision tasks.
During magnetic resonance imaging (MRI), the strong response to the signal is usually displayed as structural edges and textures, which is important for distinguishing different tissues and lesions. In the current superresolution (SR) methods with the usage of deep learning, some low-level structural information tends to gradually disappear as the network deepens, resulting in excessive smoothness in high-frequency regions. This phenomenon is particularly noticeable in MRI with poor brightness contrast and small gray dynamic range. Although the generative adversarial network (GAN) can repair structured textures well in natural images, it is likely to learn patterns that do not exist in the images, which poses risks to the reconstruction of medical images. Therefore, we propose an enhanced gradient guiding network (EG2N) to alleviate these problems. On the one hand, for improving the contrast and suppress the noise effectively, we use a multi-scale wavelet enhancement for preprocessing, where the enhanced gradient map is considered as the structural prior. On the other hand, blindly using dense connections in the feed-forward network will bring about redundancy, so structural features from an additional branch are added to specific layers as a supplement to high-level features and constrain optimization. We add a feedback mechanism to promote cross-layer flow between low-level and high-level features. In addition, the perceptual loss is added to avoid distortion caused by excessive smoothing. The experimental results show that our method achieves the best visual results and excellent performance compared with state-of-the-art methods on most popular MR images SR benchmarks.
The hyper-spectrum data exhibits the structure, materials, and semantic meaning of a nature scene and its fast acquisition is of great importance due to its potential for parse these properties of dynamic scenes. Targeting for high speed hyperspectrum imaging of a nature scene, this paper proposes to capture the coded hyper-spectrum reflectance of a nature scene using low cost hardware and reconstruct the latent data using a corresponding decoding algorithm. Except for a wide spectrum light source, the imaging system includes mainly a commercially available projector color wheel and a high speed camera, which work at their own constant periods and are self-synchronized by our algorithm. The introduced light source and color wheel cost less than 50 dollars and makes the proposed approach widely available. The results on the data captured by our prototype system show that, the proposed approach can reconstruct the high precision hyper-spectrum data at real time.
Plenoptic camera records the 4D light field data by storing the spatial information and angular information. Meanwhile, it
introduces the trade-off between spatial resolution and angular resolution. We proposed a new camera design which has
been modulated in Fourier domain. High resolution 4D light field could be reconstructed from the coded image by sparse
reconstruction. A simulation is carried out to evaluate the performance of the camera design. The reconstructed light field
has a better performance than the conventional plenoptic camera.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.