Computer Animation and Virtual Worlds最新文献

As Extended Reality (XR) technologies continue gaining popularity, various domains seek to integrate them into their workflows to enhance performance and user satisfaction. However, integrating XR technologies into emergency response presents unique challenges. Unlike other fields, such as healthcare, entertainment, or education, emergency response involves physically demanding environments and information-intensive tasks that first responders (FRs) must perform. Augmented reality (AR) head-mounted displays (HMDs) present promising solutions for improving situational awareness and reducing the cognitive load of the FRs. However, limited research has focused on the specific needs of FRs. Moreover, existing studies investigating FR needs have primarily been conducted in controlled laboratory settings, revealing a significant gap in the literature concerning FR requirements in real-life scenarios. This work addresses this gap through a comprehensive user study with subject matter experts (SMEs) and FRs. User studies were conducted after two different real-life scenarios using AR HMDs. To further understand FR needs, we extensively reviewed the literature for similar studies that reported FR needs, explicitly focusing on studies including interviews with SMEs and FRs. Our findings identified key design guidelines for FR-friendly AR interfaces while also highlighting the direction for future research to improve the user experience of the FRs.

Recently, crowd trajectory prediction has attracted increasing attention. In particular, the simulation of pedestrian movement in scenarios such as crowd evacuation has gained increasing focus. The social force model is a promising and effective method for predicting the stochastic movement of pedestrians. However, individual heterogeneity, group-driven cooperation, and poor self-adaptive environmental interactive capabilities have not been comprehensively considered. This often makes it difficult to reproduce real scenarios. Therefore, a group-enabled social force model-driven multi-agent generative adversarial imitation learning framework, namely, SFMAGAIL, is proposed. Specifically, (1) a group-enabled individual heterogeneity schema is utilized to obtain related expert trajectories, which are fully incorporated into the desire force and group-enabled paradigms; (2) A joint policy is used to exploit the connection between the agents and the environment; and (3) To explore the intrinsic features of expert trajectories, an actor–critic-based multi-agent adversarial imitation learning framework is presented to generate effective trajectories. Finally, extensive experiments based on 2D and 3D virtual scenarios are conducted to validate our method. The results show that our proposed method is superior to the compared methods.

In this paper, we propose a machine learning-driven model to optimize panoramic video transmission for multiple users in virtual reality environments. The model predicts users' future field of view (FOV) using historical head orientation data and video saliency information, enabling targeted video delivery based on individual perspectives. By segmenting panoramic videos into tiles and applying a pyramid coding scheme, we adaptively transmit high-quality content within users' FOVs while utilizing lower-quality transmissions for peripheral regions. This approach effectively reduces bandwidth consumption while maintaining a high-quality viewing experience. Our experimental results demonstrate that combining user viewpoint data with video saliency features significantly improves long-term FOV prediction accuracy, leading to a more efficient and user-centric transmission model. The proposed method holds great potential for enhancing the immersive experience of panoramic video streaming in VR, particularly in bandwidth-constrained environments.

This study focuses on transforming real-world scenery into Chinese landscape painting masterpieces through style transfer. Traditional methods using convolutional neural networks (CNNs) and generative adversarial networks (GANs) often yield inconsistent patterns and artifacts. The rise of diffusion models (DMs) presents new opportunities for realistic image generation, but their inherent noise characteristics make it challenging to synthesize pure white or black images. Consequently, existing DM-based methods struggle to capture the unique style and color information of Chinese landscape paintings. To overcome these limitations, we propose CLPFusion, a novel framework that leverages pre-trained diffusion models for artistic style transfer. A key innovation is the Bidirectional State Space Models-CrossAttention (BiSSM-CA) module, which efficiently learns and retains the distinct styles of Chinese landscape paintings. Additionally, we introduce two latent space feature adjustment methods, Latent-AdaIN and Latent-WCT, to enhance style modulation during inference. Experiments demonstrate that CLPFusion produces more realistic and artistic Chinese landscape paintings than existing approaches, showcasing its effectiveness and uniqueness in the field.

We propose a novel method, entitled “Folding by Skinning”, which creatively integrates skinning techniques with folding simulations. This method allows users to specify a two-dimensional crease pattern along with the desired folding angles for each crease. Based on this input, the system computes the final three-dimensional shape of the fold. Rather than employing costly physics-based simulations, we explore the skinning method, noted for its effectiveness in handling the geometry of the folded shape. We recommend extracting the skinning weights directly from the user-defined crease patterns. By combining the obtained skinning weights with the user-input folding angles, the initial shape undergoes dual quaternion skinning to produce the folding result. Users can further optimize the shape using post-processing and targeted filtering of weights to generate more realistic results. Our experimental results demonstrate that “Folding by Skinning” yields high-quality outcomes and offers relatively fast computation, making it an effective tool for computer-aided design, animation, and fabrication applications.

This paper presents a novel framework for generating piano performance animations using a two-stage deep learning model. By using discrete musical score data, the framework transforms sparse control signals into continuous, natural hand motions. Specifically, in the first stage, by incorporating musical temporal context, the keyframe predictor is leveraged to learn keyframe motion guidance. Meanwhile, the second stage synthesizes smooth transitions between these keyframes via an inter-frame sequence generator. Additionally, a Laplacian operator-based motion retargeting technique is introduced, ensuring that the generated animations can be adapted to different digital human models. We demonstrate the effectiveness of the system through an audiovisual multimedia application. Our approach provides an efficient, scalable method for generating realistic piano animations and holds promise for broader applications in animation tasks driven by sparse control signals.

Vertex Block Descent (VBD) is a fast and robust method for the real-time simulation of deformable objects using the finite element method. Originally, the method was designed for the popular linear tetrahedral elements. However, these elements have low accuracy and introduce locking artifacts. In this context, we propose an extension of VBD to: (i) support any isoparametric elements and shape function orders; (ii) improve its performance even for high-order elements; and (iii) enhance convergence through the use of sub-stepping. Overall, using other types of elements enables more accurate results while maintaining a computational cost comparable to linear tetrahedra.

Image denoising plays a vital role in restoring high-quality images from noisy inputs and directly impacts downstream vision tasks. Traditional methods often fail under strong noise, causing detail loss or excessive smoothing. While recent Convolutional Neural Networks-based and Transformer-based models have shown progress, they struggle to jointly capture global structure and preserve local details. To address this, we propose SCNet, a dual-branch fusion network tailored for strong-noise denoising. It combines a Swin Transformer branch for global context modeling and a ConvNeXt branch for fine-grained local feature extraction. Their outputs are adaptively merged via a Feature Fusion Block using joint spatial and channel attention, ensuring semantic consistency and texture fidelity. A multi-scale upsampling module and the Charbonnier loss further improve structural accuracy and visual quality. Extensive experiments on four benchmark datasets show that SCNet outperforms state-of-the-art methods, especially under severe noise, and proves effective in real-world tasks such as mural image restoration.

The use of generative AI to create responsive and adaptive game content has attracted considerable interest within the educational game design community, highlighting its potential as a tool for enhancing players' understanding of in-game knowledge. However, designing effective player-AI interaction to support knowledge representation remains unexplored. This paper presents AIKII, an AI-enhanced Knowledge Interaction Interface designed to facilitate knowledge representation in educational games. AIKII employs various interaction channels to represent in-game knowledge and support player engagement. To investigate its effectiveness and user learning experience, we implemented AIKII into The Journey of Poetry, an educational game centered on learning Chinese poetry, and conducted interviews with university students. The results demonstrated that our method fosters contextual and reflective connections between players and in-game knowledge, enhancing player autonomy and immersion.