Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance.

Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient in conveying the overall scene context, it may be insufficient to control precisely. In this paper, we explore customized video generation by utilizing text as context description and motion structure (e.g. frame- wise depth) as concrete guidance. Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules. This two-stage learning scheme not only reduces the computing resources required, but also improves the performance by transferring the rich concepts available in image datasets solely into video generation. Moreover, we use a simple yet effective causal attention mask strategy to enable longer video synthesis, which mitigates the potential quality degradation effectively. Experimental results show the superiority of our method over existing baselines, particularly in terms of temporal coherence and fidelity to users' guidance. In addition, our model enables several intriguing applications that demonstrate potential for practical usage. The code, model weights, and videos are publicly available at our project page: https://doubiiu.github.io/projects/Make-Your-Video/.

Deep Learning Models for Automatic Upper Airway Segmentation and Minimum Cross-Sectional Area Localisation in Two-Dimensional Images.

OBJECTIVE: To develop and validate convolutional neural network algorithms for automatic upper airway segmentation and minimum cross-sectional area (CSAmin) localisation in two-dimensional (2D) radiographic airway images. MATERIALS AND METHODS: Two hundred and one 2D airway images acquired using cone-beam computed tomography (CBCT) scanning were randomly assigned to a test group (n = 161) to train artificial intelligence (AI) models and a validation group (n = 40) to evaluate the accuracy of AI processing. Four AI models, UNet18, UNet36, DeepLab50 and DeepLab101, were trained to automatically segment the upper airway 2D images in the test group. Precision, recall, Intersection over Union, the dice similarity coefficient and size difference were used to evaluate the performance of the AI-driven segmentation models. The CSAmin height in each image was manually determined using three-dimensional CBCT data. The nonlinear mathematical morphology technique was used to calculate the CSAmin level. Height errors were assessed to evaluate the CSAmin localisation accuracy in the validation group. The time consumed for airway segmentation and CSAmin localisation was compared between manual and AI processing methods. RESULTS: The precision of all four segmentation models exceeded 90.0%. No significant differences were found in the accuracy of any AI models. The consistency of CSAmin localisation in specific segments between manual and AI processing was 0.944. AI processing was much more efficient than manual processing in terms of airway segmentation and CSAmin localisation. CONCLUSIONS: We successfully developed and validated a fully automatic AI-driven system for upper airway segmentation and CSAmin localisation using 2D radiographic airway images.

[Measuring the Spectrum of Extinction Coefficient and Reflectance for Cadmium Compounds from 400 to 900 nm].

The key to extract the contents of cadmium in water by using remote sensing technique is to measure the spectrum of extinction coefficient per g·L(-1) and reflectance for its compounds. So in this paper, firstly, we choose two kinds of cadmium compounds, cadmium sulfide (CdS) and cadmium oxide (CdO), which are most commonly exsit in natural water, to measure the spectrums of extinction coefficient and reflectance for them. We use the equipment, designed on our own, which can adjust the path length of light passing and make our measuring results more accurate at visible and near-infrared wavelength range than others. Then we use Analytical Spectral Devices (ASD) spectrometer to measure the radiance of the light spot, which is from the direct light passed through cadmium compounds solutions of different concentrations reflected by the standard board. Using the ratio method to eliminate environmental errors and the effects of the thimbleful of suspended solids in water, we obtain the extinction coefficient per g·L(-1) of these two kinds of cadmium compounds from 400 to 900 nm. Secondly, we use ASD spectrometer to measure the reflectance spectrum of them in the sunny day at outdoor. The reflectance we obtain in this paper can help us to calculate the absorption and scattering coefficient per g·L(-1) in the future. The measuring results show that the extinction coefficient spectrum of CdS has two troughs at 550 and 830 nm and one peak at 675 nm. And the extinction coefficient spectrum of CdO decrease from purple to near-infrared. Both of their coefficient spectrums in blue are larger than green and red. And the value of the extinction coefficient per g·L(-1) of CdS is larger than CdO in the whole measuring wavelength range. The reflectance of CdS in yellow and red is larger than purple and blue, which increases rapidly from 500 to 650 nm and then leveling off. While the reflectance of CdO increase linearly from 525 to 900 nm. Both have obvious spectral characteristic. According to our results, the largest extinction coefficient appear at blue color, while the largest reflectance appear at yellow and red, which means that those bands are the most sensitive wavelength to detect the change of cadmium concentration in water. This study carries out with optical parameters measurements for optical activity of cadmium compounds specifically for water quality remote sensing for the first time. We conclude that the extinction coefficient and reflectance spectrums we obtained are reasonable, and the results can be used as the base parameter in the remote sensing inversion model for cadmium contents in water, which provides a breakthrough on using remote sensing technique to extract the heavy metal contents in water. Obtained these two optical parameters in this paper can provide powerful reference for band selection of the remote sensing image, which is used to extract cadmium contents in water, as well as provide the necessary important parameters of the remote sensing inversion model of cadmium contents in water.