Text-driven video editing powered by generative diffusion models holds significant promise for applications spanning film production, advertising, and beyond. However, the limited expressiveness of pre-trained word embeddings often restricts nuanced edits, especially when targeting novel concepts with specific attributes. In this work, we present a novel Concept-Augmented Textual Inversion (CATI) framework that flexibly integrates new object information from user-provided concept videos. By fine-tuning only the V (Value) projection in attention via Low-Rank Adaptation (LoRA), our approach preserves the original attention distribution of the diffusion model while efficiently incorporating external concept knowledge. To further stabilize editing results and mitigate the issue of attention dispersion when prompt keywords are modified, we introduce a Dual Prior Supervision (DPS) mechanism. DPS supervises cross-attention between the source and target prompts, preventing undesired changes to non-target areas and improving the fidelity of novel concepts. Extensive evaluations demonstrate that our plug-and-play solution not only maintains spatial and temporal consistency but also outperforms state-of-the-art methods in generating lifelike and stable edited videos. The source code is publicly available at https://guomc9.github.io/STIVE-PAGE/.

Cinemagraph creates captivating video experience by combining elements of still photography and subtle motion. However, most existing cinemagraph video generation lacks depth information, being restricted within 2-dimensional (2D) image space. We advance cinemagraph from 2D image space to 3-dimensional (3D) space with high quality by proposing LoopGaussian. It is based on 3D Gaussian modeling, taking advantage of the 3D Gaussian Splatting (3D-GS) technique that has significantly improved the field of novel view synthesis. Here is a brief overview of our new approach: It employs 3D-GS to reconstruct 3D Gaussian point clouds from multi-view images of static scenes, where shape regularization is used to prevent blurring or artifacts caused by object deformation. To maintain local continuity between scenes, it then clusters the 3D Gaussian points by the proposed SuperGaussian algorithm using features acquired by an autoencoder tailored for 3D Gaussian. Similarities between clusters are used to derive an Eulerian motion field for describing velocities across the entire scene. The estimated Eulerian motion field drives the movement of the 3D Gaussian points, based on which a 3D Cinemagraph is generated through bidirectional animation. The resulting 3D Cinemagraph exhibits natural and seamlessly loopable dynamics. Experiment results validate the effectiveness of the proposed approach, demonstrating high-quality and visually appealing video generation.

In the realm of multi-modality, text-guided image retouching techniques emerged with the advent of deep learning. Most currently available text-guided methods, however, rely on object-level supervision to confine the region of interest that may be updated. This not only makes it more challenging to develop these algorithms but also limits how widely deep learning can be used for image retouching. In this paper, we offer a text-guided mask-free image retouching approach that yields consistent results to address this concern. Specifically, we propose a two-stage mask-free training paradigm tailored for text-guided image retouching tasks. In the first stage, an unified mask is proposed according to the query description, and then several candidate images are generated with the provided mask and the conditional description based on diffusion model. Extensive experiments have shown that our method can produce high-quality images based on spoken language.

With the rapid development of sensing technologies, massive spatiotemporal data have been acquired from the urban space with respect to different domains, such as transportation and environment. Numerous co-occurrence patterns (e.g., traffic speed <; 10km/h, weather = foggy, and air quality = unhealthy) between the transportation data and other types of data can be obtained with given spatiotemporal constraints (e.g., within 3 kilometers and lasting for 2 hours) from these heterogeneous data sources. Such patterns present valuable implications for many urban applications, such as traffic management, pollution diagnosis, and transportation planning. However, extracting and understanding these patterns is beyond manual capability because of the scale, diversity, and heterogeneity of the data. To address this issue, a novel visual analytics system called CorVizor is proposed to identify and interpret these co-occurrence patterns. CorVizor comprises two major components. The first component is a co-occurrence mining framework involving three steps, namely, spatiotemporal indexing, co-occurring instance generation, and pattern mining. The second component is a visualization technique called CorView that implements a level-of-detail mechanism by integrating tailored visualizations to depict the extracted spatiotemporal co-occurrence patterns. The case studies and expert interviews are conducted to demonstrate the effectiveness of CorVizor.

Brain–computer interface is a new form of interaction between humans and machines. This interaction helps the human brain control or operate external devices directly using electroencephalograph (EEG) signals. In this study, we first adopt a canonical correlation analysis method to find the stimulation frequency by calculating the correlation coefficient between the EEG data and multiple sets of harmonics with different frequencies. Then, we select the maximum correlation coefficient as the stimulus frequency and consequently identify steady-state visual evoked potentials. Afterward, we introduce power spectral density to adjust the stimulus frequency and a voting mechanism to reduce the false activation rate. Finally, we build a virtual household electrical appliance brain–computer control interface, which achieves over 72.84% accuracy for three classification problems.

Social data refers to data individuals create that is knowingly and voluntarily shared by them and is an exciting avenue into gaining insight into interpersonal behaviors and interaction. However, such data is large, heterogeneous and often incomplete, properties that make the analysis of such data extremely challenging. One common method of exploring such data is through cluster analysis, which can enable analysts to find groups of related users, behaviors and interactions. This paper presents a novel visual analysis approach for detecting clusters within large-scale social networks by utilizing a divide-analyze-recombine scheme that sequentially performs data partitioning, subset clustering and result recombination within an integrated visual interface. A case study on a microblog messaging data (with 4.8 millions users) is used to demonstrate the feasibility of this approach and comparisons are also provided to illustrate the performance benefits of this approach with respect to existing solutions.

Many applications involve map visualization. Nevertheless, almost all of them display the map in the same style, which often cause information overloading. In this paper, we present a novel user-centered 2.5D focus context map visualization technique. Instead of treating all the information equally, we can custom the map according to user requirements. The main contributions of our technique are in three aspects. Firstly, our system can automatically construct a hierarchical representation of the city according to the focus point of the users by using the R-trees data structure, then presenting users the map in multiple rendering styles, highlighting the user concerned information and deemphasizing the less important information. Secondly, a landmark margin is automatically added to the original map according to the points-of-interest(POI), which illustrates the context information and enables users to maintain a macro view of the city. Moreover, by applying the 2.5D technique, we can reduce the amount of data and accelerate the transport of the information. The results show that our user-centered map visualization technique can greatly improve the efficiency for users to get their concerned information.

In this paper, we present a new adaptive model for real-time fluid simulation with complex boundaries based on smoothed particle hydrodynamics (SPH) framework. Firstly, we introduce an adaptive SPH framework that is based on our character field function composed of 4 factors: geometrical complexity, boundary condition, physical complexity and complementary condition in terms of the neighboring particle number. Meanwhile, the rule for particle adaptation is presented. We also present a two-step method to fast detect collision with complex boundary. The first step is voxelization on the complex scene. In the second step, based on the result of voxelization, we propose a three-phase method to fast detect collisions between complex boundaries and particles. By using this method, we avoid most of the useless intersection detection computation and greatly enhance the computation efficiency. In addition, a subdivision of boundary is pre-computed before the collision interaction method so that fluid in a scene with complex boundary can still be simulated at relatively high speed and system stability risk is reduced greatly. To further accelerate the simulation, a highly parallel fluid algorithm is presented and implemented using GPU so that we can simulate dynamic fluid with mutual interaction between fluid and complex boundary at a considerably fast speed without compromising realism.

Abstract We present a new adaptive model for real‐time fluid simulation based on Smoothed Particle Hydrodynamics (SPH) framework. Unlike traditional time‐consuming SPH methods, our model can simulate fluid at a considerably faster speed without losing realism. In our model, we first introduce the non‐uniform particle system and propose a generalized distance field function which considers not only geometrical complexity but also physical complexity of fluid body. And the new sampling rules for splitting and merging of particles are also presented. This can greatly reduce the computation time of the dynamic fluid simulation. Then, a new pressure state equation and an adaptive surface tension model are proposed to enhance the stability of the system and to make the free surface more realistic. To further accelerate the computation, a special fluid solver is designed and implemented using GPU. Various fluid phenomena like breaking wave and flood are simulated at real‐time. Experiments demonstrate that our new adaptive model can greatly enhance the computation efficiency of fluid simulation compared with previous adaptive methods. Copyright © 2009 John Wiley & Sons, Ltd.

In this paper, we exploit the level set methods to extract and analyze the feature of macromolecular field. For the 3D volume data of the field, we propose a novel variational formulation of the geometric active contour, which is composed of an external energy to drive the active contours' motion, and an internal energy which penalizes the level set function adoptively to avoid periodically re-initializing. We adjust the parameters of each component and examine their influences in the whole process. Our approach provides an intuitive way to study spatial relationships of the segmented regions. And it is shown to be more accurate and efficient on the feature extraction regarding the HIV-1 protease molecular field and the DPS protein molecular field. During the exploration, we successfully found the escape route of water molecules hidden in the HIV-1 protease and the internal cavity of the DPS protein for the iron atom 's entry and deposition, which are both in accordance with the experimental results.

Fast display of realistic dynamic cloud scene is a challenging task for researchers in computer graphics. This paper describes a novel method of simulating animations of cloud. We first model the motion of cloud based on the physical theory of cloud formation. Then, the physical model of cloud is solved in discrete sparse grids. Thus, we can get approximate motion of cloud. Next, we advect texture image using the calculated velocity field to add the local detail of dynamic cloud scene. Here the texture image we used is Perlin noise map. The color of arbitrary point in the simulation space is got by calculating the product of the density texture and the regenerated Perlin noise texture. Finally, by changing different noise maps, realistic dynamic cloud scenes in different light environment are generated at high rendering rates.

Abstract This paper describes a physically based method for modeling and animating sandstorm, a type of disastrous natural phenomenon. The method adopts a relatively stable incompressible multiple fluid model to simulate the motion of air, sand, and dust particles. The wind field of sandstorm is established based on Reynold‐average Navier‐Stokes equations. The sand and dust particle flow is therefore computed taking interaction among the wind, sand, and dust particles into account. To accelerate the modeling process of a dynamic sandstorm scene, a special Multi‐Fluid Solver is designed and implemented on GPU. Various illumination effects of sandstorm scenes can be simulated by spectral sampling scattering calculation. Animations of realistic sandstorms occurring in desert and urban areas based on our model are demonstrated. Compared with the real sandstorm photos, our simulated results are satisfactory. Copyright © 2007 John Wiley & Sons, Ltd.

Abstract Realistic rendering of sky scene is important in game development and virtual reality. Traditional methods did not consider both the affect of atmospheric scattering and refraction, thus failing to realistically simulate the change of shape, color, and light ring of sky scene. In this paper, a new sky light model considering atmospheric scattering and refraction is proposed. We first calculate the refractional track of light through the atmosphere according to the refraction index. Then we adopt the scattered volume model to simplify the calculation of scattering light intensity. By adapting a path tracing algorithm considering refraction, the intensity distribution of sky light is calculated. Finally, various sky scenes in sunny day, foggy day, and that with rainbow and mirage under different conditions are realistically rendered in real time. Copyright © 2007 John Wiley & Sons, Ltd.

Abstract Simulation of dynamic natural scene is one of the most challenging tasks in computer graphics. In this paper, we propose a new approach to dynamic modeling and rendering of grasses wagging in wind. Through length preserving free‐form deformation of the 3D skeleton lines of each grass blade and using the alpha test to implement transparent texture mapping, we successfully model grasses of different shapes with rich details. To simulate the real time waggle of grasses, the grasses of a meadow are represented in LOD, while their skeleton lines are dynamically deformed according to some physical models. Simplification technique is also employed to accelerate the collision detection between neighboring grasses. Experiments show that our method can realistically render the animated grass scenes under wind of different speeds and types in real time. Copyright © 2005 John Wiley & Sons, Ltd.