Computer Animation and Virtual Worlds最新文献

Neural Radiance Field (NeRF) can render complex 3D scenes with viewpoint-dependent effects. However, less work has been devoted to exploring its limitations in high-resolution environments, especially when upscaled to ultra-high resolution (e.g., 4k). Specifically, existing NeRF-based methods face severe limitations in reconstructing high-resolution real scenes, for example, a large number of parameters, misalignment of the input data, and over-smoothing of details. In this paper, we present a novel and effective framework, called De-NeRF, based on NeRF and deformable convolutional network, to achieve high-fidelity view synthesis in ultra-high resolution scenes: (1) marrying the deformable convolution unit which can solve the problem of misaligned input of the high-resolution data. (2) Presenting a density sparse voxel-based approach which can greatly reduce the training time while rendering results with higher accuracy. Compared to existing high-resolution NeRF methods, our approach improves the rendering quality of high-frequency details and achieves better visual effects in 4K high-resolution scenes.

Streamlines are a popular method of choice in many flow visualization techniques due to their simplicity and intuitiveness. This paper presents a novel streamline seeding method, which is tailored for visualizing unsteady flow in augmented reality (AR). Our method prioritizes visualizing the visible part of the flow field to enhance the flow representation's quality and reduce the computational cost. Being an image-based method, it evenly samples 2D seeds from the screen space. Then, a ray is fired toward each 2D seed, and the on-the-ray point, which has the largest entropy, is selected. It is taken as the 3D seed for a streamline. By advecting such 3D seeds in the velocity field, which is continuously updated in real time, the unsteady flow is visualized more naturally, and the temporal coherence is achieved with no extra efforts. Our method is tested using an AR application for visualizing airflow from a virtual air conditioner. Comparison with the baseline methods shows that our method is suitable for visualizing unsteady flow in AR.

Reconstructing the three-dimensional (3D) shape and texture of the face from a single image is a significant and challenging task in computer vision and graphics. In recent years, learning-based reconstruction methods have exhibited outstanding performance, but their effectiveness is severely constrained by the scarcity of available training data with 3D annotations. To address this issue, we present the PR3D (Precise and Realistic 3D face reconstruction) method, which consists of high-precision shape reconstruction based on semi-supervised learning and high-fidelity texture reconstruction based on StyleGAN2. In shape reconstruction, we use in-the-wild face images and 3D annotated datasets to train the auxiliary encoder and the identity encoder, encoding the input image into parameters of FLAME (a parametric 3D face model). Simultaneously, a novel semi-supervised hybrid landmark loss is designed to more effectively learn from in-the-wild face images and 3D annotated datasets. Furthermore, to meet the real-time requirements in practical applications, a lightweight shape reconstruction model called fast-PR3D is distilled through teacher–student learning. In texture reconstruction, we propose a texture extraction method based on face reenactment in StyleGAN2 style space, extracting texture from the source and reenacted face images to constitute a facial texture map. Extensive experiments have demonstrated the state-of-the-art performance of our method.

Within the field of human–computer interaction, data gloves play an essential role in establishing a connection between virtual and physical environments for the realization of digital human. To enhance the credibility of human-virtual hand interactions, we aim to develop a system incorporating a data glove-embedded technology. Our proposed system collects a wide range of information (temperature, bending, and pressure of fingers) that arise during natural interactions and afterwards reproduce them within the virtual environment. Furthermore, we implement a novel traversal polling technique to facilitate the streamlined aggregation of multi-channel sensors. This mitigates the hardware complexity of the embedded system. The experimental results indicate that the data glove demonstrates a high degree of precision in acquiring real-time hand interaction information, as well as effectively displaying hand posture in real-time using Unity3D. The data glove's lightweight and compact design facilitates its versatile utilization in virtual reality interactions.

We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the $��m�A�{�P�}_{�50�-�95�}�$ of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations.

Simulation of swarm motion is a crucial research area in computer graphics and animation, and is widely used in a variety of applications such as biological behavior research, robotic swarm control, and the entertainment industry. In this paper, we address the challenges of preserving structural relations between the individuals in swarm flight simulations by proposing an innovative motion control framework that utilizes a graph-based hierarchy to illustrate patterns within a swarm and allows the swarm to perform flight motions along externally specified paths. In addition, this study designs motion propagation strategies with different focuses for varied application scenarios, analyzes the effects of information transfer latencies on pattern preservation under these strategies, and optimizes the control algorithms at the mathematical level. This study not only establishes a complete set of control methods for group flight simulations, but also has excellent scalability, which can be combined with other techniques in this field to provide new solutions for group behavior simulations.

In computer vision, the task of 3D reconstruction from monocular sparse images poses significant challenges, particularly in the field of animal modelling. The diverse morphology of animals, their varied postures, and the variable conditions of image acquisition significantly complicate the task of accurately reconstructing their 3D shape and pose from a monocular image. To address these complexities, we propose S-LASSIE, a novel technique for 3D reconstruction of quadrupeds from monocular sparse images. It requires only 10–30 images of similar breeds for training. To effectively mitigate depth ambiguities inherent in monocular reconstructions, S-LASSIE employs a multi-angle projection loss function. In addition, our approach, which involves fusion and smoothing of bone structures, resolves issues related to disjointed topological structures and uneven connections at junctions, resulting in 3D models with comprehensive topologies and improved visual fidelity. Our extensive experiments on the Pascal-Part and LASSIE datasets demonstrate significant improvements in keypoint transfer, overall 2D IOU and visual quality, with an average keypoint transfer and overall 2D IOU of 59.6% and 86.3%, respectively, which are superior to existing techniques in the field.

Improving the accuracy and disentanglement of attribute translation, and maintaining the consistency of face identity have been hot topics in face attribute translation. Recent approaches employ attention mechanisms to enable attribute translation in facial images. However, due to the lack of accuracy in the extraction of style code, the attention mechanism alone is not precise enough for the translation of attributes. To tackle this, we introduce a style translator module, which partitions the style code into attribute-related and unrelated components, enhancing latent space disentanglement for more accurate attribute manipulation. Additionally, many current methods use per-pixel loss functions to preserve face identity. However, this can sacrifice crucial high-level features and textures in the target image. To address this limitation, we propose a multiple-perceptual reconstruction loss to better maintain image fidelity. Extensive qualitative and quantitative experiments in this article demonstrate significant improvements over state-of-the-art methods, validating the effectiveness of our approach.

Evacuation scene simulation has become one important approach for public safety decision-making. Although existing research has considered various factors, including social forces, panic emotions, and so forth, there is a lack of consideration of how complex environmental factors affect human psychology and behavior. The main idea of this paper is to model complex evacuation environmental factors from the perspective of knowledge and explore pedestrians' emergency response mechanisms to this knowledge. Thus, a knowledge-driven dynamic perception model (KDPM) for evacuation scene simulation is proposed in this paper. This model combines three modules: knowledge dissemination, dynamic scene perception, and stress response. Both scenario knowledge and hazard source knowledge are extracted and expressed. The improved intelligent agent perception model is designed by adopting position determination. Moreover, a general adaptation syndrome (GAS) model is first presented by introducing a modified stress system model. Experimental results show that the proposed model is closer to the reality of real data sets.