FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing.

Existing facial editing methods have achieved remarkable results, yet they often fall short in supporting multimodal conditional local facial editing. One of the significant evidences is that their output image quality degrades dramatically after several iterations of incremental editing, as they do not support local editing. In this paper, we present a novel multimodal generative and fusion framework for globally-consistent local facial editing (FACEMUG) that can handle a wide range of input modalities and enable fine-grained and semantic manipulation while remaining unedited parts unchanged.

A Bio-inspired Model for Bee Simulations.

As eusocial creatures, bees display unique macro collective behavior and local body dynamics that hold potential applications in various fields, such as computer animation, robotics, and social behavior. Unlike birds and fish, bees fly in a low-aligned zigzag pattern. Additionally, bees rely on visual cues for foraging and predator avoidance, exhibiting distinctive local body oscillations, such as body lifting, thrusting, and swaying.

Interfacial Polymerization on Polyethersulfone Ultrafiltration Membrane to Prepare Nanofiltration Layers for Dye Separation.

Nanofiltration membranes are of great significance to the treatment of dye wastewater. Interfacial polymerization is a widely used method to fabricate nanofiltration membranes. In this study, the interaction of tannic acid-assisted polyethylene polyamine (PEPA) with terephthalaldehyde (TPAL) was performed on PES ultrafiltration membranes using novel nitrogen-rich amine monomers and relatively less reactive aldehyde-based monomers.

Multi-Granularity Context Network for Efficient Video Semantic Segmentation.

Current video semantic segmentation tasks involve two main challenges: how to take full advantage of multi-frame context information, and how to improve computational efficiency. To tackle the two challenges simultaneously, we present a novel Multi-Granularity Context Network (MGCNet) by aggregating context information at multiple granularities in a more effective and efficient way. Our method first converts image features into semantic prototypes, and then conducts a non-local operation to aggregate the per-frame and short-term contexts jointly.

MNSS: Neural Supersampling Framework for Real-Time Rendering on Mobile Devices.

Although neural supersampling has achieved great success in various applications for improving image quality, it is still difficult to apply it to a wide range of real-time rendering applications due to the high computational power demand. Most existing methods are computationally expensive and require high-performance hardware, preventing their use on platforms with limited hardware, such as smartphones. To this end, we propose a new supersampling framework for real-time rendering applications to reconstruct a high-quality image out of a low-resolution one, which is sufficiently lightweight to run on smartphones within a real-time budget.

MobileSky: Real-Time Sky Replacement for Mobile AR.

We present MobileSky, the first automatic method for real-time high-quality sky replacement for mobile AR applications. The primary challenge of this task is how to extract sky regions in camera feed both quickly and accurately. While the problem of sky replacement is not new, previous methods mainly concern extraction quality rather than efficiency, limiting their application to our task.

Inner Surface Hydrophilic Modification of PVDF Membrane with Tea Polyphenols/Silica Composite Coating.

The use of Polyvinylidene fluoride (PVDF) membranes is constrained in wastewater treatment because of their hydrophobic nature. Therefore, a large number of researchers have been working on the hydrophilic modification of their surfaces. In this work, a superhydrophilic tea polyphenols/silica composite coating was developed by a one-step process.

A Calibrated Force-Based Model for Mixed Traffic Simulation.

Virtual traffic benefits a variety of applications, including video games, traffic engineering, autonomous driving, and virtual reality. To date, traffic visualization via different simulation models can reconstruct detailed traffic flows. However, each specific behavior of vehicles is always described by establishing an independent control model.

AgentDress: Realtime Clothing Synthesis for Virtual Agents using Plausible Deformations.

We present a CPU-based real-time cloth animation method for dressing virtual humans of various shapes and poses. Our approach formulates the clothing deformation as a high-dimensional function of body shape parameters and pose parameters. In order to accelerate the computation, our formulation factorizes the clothing deformation into two independent components: the deformation introduced by body pose variation (Clothing Pose Model) and the deformation from body shape variation (Clothing Shape Model).

Person Foreground Segmentation by Learning Multi-Domain Networks.

Separating the dominant person from the complex background is significant to the human-related research and photo-editing based applications. Existing segmentation algorithms are either too general to separate the person region accurately, or not capable of achieving real-time speed. In this paper, we introduce the multi-domain learning framework into a novel baseline model to construct the Multi-domain TriSeNet Networks for the real-time single person image segmentation.

Polyelectrolyte-calcium complexes as a pre-precursor induce biomimetic mineralization of collagen.

Polyelectrolytes such as polyaspartic acid (PAsp) are critical in biomimetic mineralization as stabilizers of amorphous calcium phosphate (ACP) precursors and as nucleation inhibitors similar to non-collagenous proteins (NCPs). Nevertheless, the application of polyelectrolyte-calcium complexes as a pre-precursor, such as PAsp-Ca complexes, in the mineralization of collagen is unexplored. Herein, we propose a polyelectrolyte-Ca complex pre-precursor (PCCP) process for collagen mineralization.

3D Upper Body Reconstruction with Sparse Soft Sensors.

Three-dimensional (3D) reconstruction of human body has wide applications, for example, for customized design of clothes and digital avatar production. Existing vision-based systems for 3D body reconstruction require users to wear minimal or extreme-tight clothes in front of cameras, and thus suffer from privacy problems. In this work, we explore a novel solution based on a sparse number of soft sensors on a standard garment, and use it for capturing 3D upper body shape.

Endogenetic structure of filter bubble in social networks.

The filter bubble is an intermediate structure to provoke polarization and echo chambers in social networks, and it has become one of today's most urgent issues for social media. Previous studies usually equated filter bubbles with community structures and emphasized this exogenous isolation effect, but there is a lack of full discussion of the internal organization of filter bubbles. Here, we design an experiment for analysing filter bubbles taking advantage of social bots.

Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking.

In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the relationship among the multitude of samples as they only rely on the pairs of instances for training. In this paper, we propose a new quadruplet deep network to examine the potential connections among the training instances, aiming to achieve a more powerful representation.

Submodular Function Optimization for Motion Clustering and Image Segmentation.

In this paper, we propose a framework of maximizing quadratic submodular energy with a knapsack constraint approximately, to solve certain computer vision problems. The proposed submodular maximization problem can be viewed as a generalization of the classic 0/1 knapsack problem. Importantly, maximization of our knapsack constrained submodular energy function can be solved via dynamic programing.

Dictionary-based Fidelity Measure for Virtual Traffic.

Aiming at objectively measuring the realism of virtual traffic flows and evaluating the effectiveness of different traffic simulation techniques, this paper introduces a general, dictionary-based learning method to evaluate the fidelity of any traffic trajectory data. First, a traffic pattern dictionary that characterizes common patterns of real-world traffic behavior is built offline from pre-collected ground truth traffic data. The corresponding learning error is set as the benchmark of the dictionary-based traffic representation.

Group-based rewiring rules of binary opinion competition dynamics.

The dynamics of competing opinions on networks has attracted multi-disciplinary research. Most modelling approaches assume uniform or heterogeneous behaviour among all individuals, while the role of distinctive group behaviour is rarely addressed. Here, we consider competition occurring between two opinion groups with bound rewiring rules, i.

Solid Mathematical Marbling.

Years of research have been devoted to computer-generated two-dimensional marbling. However, three-dimensional marbling has yet to be explored. In this paper, we present mathematical marbling of three-dimensional solids which supports a compact random-access vector representation.

Parametric Reshaping of Portrait Images for Weight-change.

We present an easy-to-use parametric image retouching method for thinning or fattening a face in a single portrait image while maintaining a close similarity to the source image. First, our method reconstructs a 3D face from the input face image using a morphable model. Second, according to the linear regression equation derived from the depth statistics of the soft tissue in the face and the user-set parameters of weight-change degree, we calculate the new positions of the feature points.

Coupling effect of nodes popularity and similarity on social network persistence.

Network robustness represents the ability of networks to withstand failures and perturbations. In social networks, maintenance of individual activities, also called persistence, is significant towards understanding robustness. Previous works usually consider persistence on pre-generated network structures; while in social networks, the network structure is growing with the cascading inactivity of existed individuals.

Realistic Data-Driven Traffic Flow Animation Using Texture Synthesis.

We present a novel data-driven approach to populate virtual road networks with realistic traffic flows. Specifically, given a limited set of vehicle trajectories as the input samples, our approach first synthesizes a large set of vehicle trajectories. By taking the spatio-temporal information of traffic flows as a 2D texture, the generation of new traffic flows can be formulated as a texture synthesis process, which is solved by minimizing a newly developed traffic texture energy.

Creative Virtual Tree Modeling Through Hierarchical Topology-Preserving Blending.

We present a new method to efficiently generate a set of morphologically diverse and inspiring virtual trees through hierarchical topology-preserving blending, aiming to facilitate designers' creativity production. By maintaining the topological consistency of the tree branches, sequences of similar yet different trees and novel intermediate trees with encouragingly interesting structures are generated by performing inner-species and cross-species blending, respectively. Hierarchical fuzzy correspondences are automatically established between two or multiple trees based on the multi-scale topology tree representations.

Simulating Flying Insects Using Dynamics and Data-Driven Noise Modeling to Generate Diverse Collective Behaviors.

We present a biologically plausible dynamics model to simulate swarms of flying insects. Our formulation, which is based on biological conclusions and experimental observations, is designed to simulate large insect swarms of varying densities. We use a force-based model that captures different interactions between the insects and the environment and computes collision-free trajectories for each individual insect.