Computer Animation and Virtual Worlds最新文献

To achieve efficient querying of BIM products in large-scale virtual scenes, this study introduces a Weisfeiler-Lehman (WL) kernel augmented representation for Building Information Modeling(BIM) products based on Product Attributed Graphs (PAGs). Unlike conventional data-driven approaches that demand extensive labeling and preprocessing, our method directly processes raw BIM product data to extract stable semantic and geometric features. Initially, a PAG is constructed to encapsulate product features. Subsequently, a WL kernel enhanced multi-channel node aggregation strategy is employed to integrate BIM product attributes effectively. Leveraging the bijective relationship in graph isomorphism, an unsupervised convergence mechanism based on attribute value differences is established. Experiments demonstrate that our method achieves convergence within an average of 3 iterations, completes graph isomorphism testing in minimal time, and attains an average query accuracy of 95%. This approach outperforms 1-WL and 3-WL methods, especially in handling products with topologically isomorphic but oppositely attributed spaces.

This paper introduces a reinforcement learning method to simulate agents crossing roads in unsignalized, mixed-traffic environments. These agents represent individual pedestrians or small groups. The method ensures that agents adopt safe interactions with nearby dynamic obstacles (bikes, motorcycles, or cars) by considering factors such as conflict zones and post-encroachment times. Risk assessments based on interaction times encourage agents to avoid hazardous behaviors. Additionally, risk-informed reward terms incentivize agents to perform safe actions, while collision penalties deter collisions. The method achieved collision-free crossings and demonstrated normal, conservative, and aggressive pedestrian behaviors in various scenarios. Finally, ablation tests revealed the impact of reward weights, reward terms, and key agent state components. The weights of reward terms can be adjusted to achieve either conservative or aggressive pedestrian crossing behaviors, balancing road crossing efficiency and safety.

Motion in-betweening is a flexible and efficient technique for generating 3-dimensional animations. In this paper, we propose a keyframe-driven method that effectively addresses the pose ambiguity issue and achieves robust in-betweening performance. We introduce a keyframe-driven synthesis framework. At each recursion, the key poses at both ends keep predicting the new one at the midpoint. The recursive breakdown reduces motion ambiguities by simplifying the in-betweening sequence as the integration of short clips. The hybrid positional encoding scales the hidden states to adapt to long- and short-term dependencies. Additionally, we employ a temporal refinement network to capture the local motion relationships, thereby enhancing the consistency of the predicted pose sequence. Through comprehensive evaluations that include both quantitative and qualitative comparisons, the proposed model demonstrates its competitiveness in prediction accuracy and in-betweening flexibility.

High-fidelity 3D face morphing aims to achieve seamless transitions between realistic 3D facial representations of different identities. Although 3D Gaussian Splatting (3DGS) excels in high-quality rendering, its application to morphing is hindered by the lack of Gaussian primitive correspondence and variations in primitive quantities. To address this, we propose GSFaceMorpher, which is a novel framework for high-fidelity 3D face morphing based on 3DGS. Our method constructs an auxiliary model that bridges the source and target face models by aligning the geometry through Radial Basis Function (RBF) warping and optimizing the appearance in the image space. This auxiliary model enables smooth parameter interpolation, whereas a diffusion-based refinement step enhances critical facial details through attention replacement from the reference faces. Experiments demonstrate that our method produces visually coherent and high-fidelity morphing sequences, significantly outperforming NeRF-based baselines in terms of both quantitative metrics and user preferences. Our work establishes a new benchmark for high-fidelity 3D face morphing with applications in visual effects, animation, and immersive experiences.

This paper presents a control simulation that represents user-desired shapes using multiple connected soap bubbles. A previous method attempted to control a single soap bubble using external forces. However, due to the strong surface tension making spherical babbles, elongated shapes could not be achieved. To address this issue, this paper aims to develop a control simulation that achieves diverse soap bubble shapes by dividing the target shape into connected soap bubbles. In our approach, we first generate an initial soap bubble configuration composed of multiple bubbles to represent the target shape. Then, by applying external forces to each bubble, we simulate the bubbles to maintain their shape along the target form. We use an implicit-function-like representation for the connected soap bubbles and develop a new polygonizer that makes shapes including the internal faces of bubbles. By demonstrating examples with various target shapes such as objects and text, we show the effectiveness of our proposed control method.

Large Language Models (LLMs) offer almost immediate human-like quality responses to user queries. Conversational agent systems support natural language dialogues utilizing LLM backends in combination with Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) technologies, enabling life-like characters in virtual environments. This study investigates the relationship between user personality and perceived agent personality in LLM-based natural language dialogue. We adopt a Virtual Reality (VR) setting where the user can talk with the agent that assumes the role of Socrates, the famous philosopher. To this end, we utilize a three-dimensional (3D) avatar model resembling Socrates and use specific LLM prompts to get stylistic answers from OpenAI's Chat Completions Application Programming Interface (API). Our user study measures the agent's personality and the system's ease of use, quality, realism, and immersion concerning the user's self-reported personality. The results suggest that the user's conscientiousness, extraversion, and emotional stability have a moderate effect on certain personality factors and system qualities. User conscientiousness affects the perceived ease of use, quality, and realism, while user extraversion affects perceived agent conscientiousness, system realism, and immersion. Additionally, the user's emotional stability correlates with perceived extraversion and agreeableness.

Sampled point clouds, particularly with prelabeled annotations and ground truth metrics, are frequently used in computer graphics and machine learning. In this work, we focus on a fuzzy sampling approach for such point clouds with qualified uniformity properties. After abstracting the uniformity requirements, a novel approach to sampling point clouds from implicitly defined curves/surfaces is proposed. The approach deliberately combines techniques including isodeviation dispatch, curvature compensation, and normalized distance blue noise. The experimental results show various sampled point clouds with uniform visual effects and statistical metrics. Moreover, the comparisons in terms of distance, density, and thickness uniformity with state-of-the-art methods exhibit the approach's advantages. Due to its low cost, ground truth, and annotation easiness features, the method will be smoothly applied in deep learning and computer animation.

As quintessential cultural symbols in traditional shadow puppetry, artistic motifs encapsulate profound historical narratives and serve as vital conduits for intangible cultural heritage preservation. However, this craft confronts existential threats from digital entertainment proliferation and practitioner attrition. To address these challenges, this study proposes CSPMotifsGAN, an enhanced CycleGAN framework for constructing a motif data set through three-stage processing: adaptive denoising, hierarchical classification, and multi-branch feature extraction (contour, texture, color). By integrating adversarial loss, cycle-consistency loss, and identity preservation loss, the model effectively resolves color distortion and textural degradation inherent in conventional CycleGAN. Experimental results demonstrate significant improvements: Fréchet Inception Distance (FID), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM), validated through both subjective evaluations and statistical analysis.