Computer Animation and Virtual Worlds最新文献_第8页

SinMDGan: A Hybrid Deep Learning Framework for Single Motion Synthesis Using Diffusion-GAN Models SinMDGan：使用扩散- gan模型进行单运动合成的混合深度学习框架

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2026-01-16 DOI: 10.1002/cav.70091

Qiang Chen, Binsong Zuo, Tingsong Lu, Yuming Fang, Xiaolu Mu, Chao Cai, Xiaogang Jin

{"title":"SinMDGan: A Hybrid Deep Learning Framework for Single Motion Synthesis Using Diffusion-GAN Models","authors":"Qiang Chen, Binsong Zuo, Tingsong Lu, Yuming Fang, Xiaolu Mu, Chao Cai, Xiaogang Jin","doi":"10.1002/cav.70091","DOIUrl":"https://doi.org/10.1002/cav.70091","url":null,"abstract":"<div>\u0000 \u0000 <p>Generating diverse and realistic movements has long been a central challenge in computer graphics. Generative Adversarial Networks (GANs) remain a compelling solution due to their ability to perform well even with limited training data. However, traditional GANs generate samples directly, which can lead to the omission of certain data patterns. To address this limitation, we introduce <i>SinMDGan</i>, a hybrid deep learning framework for single-motion synthesis that leverages a Diffusion-GAN model. Our approach integrates the strengths of GANs, which capture global motion characteristics, with diffusion techniques, which refine local details, ensuring both authenticity and diversity in generated movements. Unlike conventional cascaded GANs, our framework employs a single generator-discriminator pair, utilizing different diffusion time steps to synthesize novel and diverse motions from a single short sequence. Experimental evaluations demonstrate the effectiveness of our model in achieving stable data distribution coverage and enhancing output diversity. Additionally, we showcase various applications, including motion composition and long-sequence generation, highlighting the versatility of our approach.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146007850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Text-Driven High-Quality 3D Human Generation via Variational Gradient Estimation and Latent Reward Models 文本驱动的高质量3D人类生成通过变分梯度估计和潜在奖励模型

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2026-01-08 DOI: 10.1002/cav.70089

Pengfei Zhou, Xukun Shen, Yong Hu

{"title":"Text-Driven High-Quality 3D Human Generation via Variational Gradient Estimation and Latent Reward Models","authors":"Pengfei Zhou, Xukun Shen, Yong Hu","doi":"10.1002/cav.70089","DOIUrl":"https://doi.org/10.1002/cav.70089","url":null,"abstract":"<div>\u0000 \u0000 <p>Recent advances in Score Distillation Sampling (SDS) have enabled text-driven 3D human generation, yet the standard classifier-free guidance (CFG) framework struggles with semantic misalignment and texture oversaturation due to limited model capacity. We propose a novel framework that decouples conditional and unconditional guidance via a dual-model strategy: A pretrained diffusion model ensures geometric stability, while a preference-tuned latent reward model enhances semantic fidelity. To further refine noise estimation, we introduce a lightweight U-shaped Swin Transformer (U-Swin) that regularizes predicted noise against the reward model, reducing gradient bias and local artifacts. Additionally, we design a time-varying noise weighting mechanism to dynamically balance the two guidance signals during denoising, improving stability and texture realism. Extensive experiments show that our method significantly improves alignment with textual descriptions, enhances texture details, and outperforms state-of-the-art baselines in both visual quality and semantic consistency.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"37 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145963945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Environmental Design Elements in Library Spaces: A Virtual Reality Study of Psychophysiological Responses to Color, Material, and Lighting in Built Environments 图书馆空间中的环境设计元素：对建筑环境中色彩、材料和照明的心理生理反应的虚拟现实研究

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2026-01-07 DOI: 10.1002/cav.70092

Mengyan Lin, Ning Li

引用次数: 0

Innovating 3D Object Generation for the Metaverse Through Speech Input 通过语音输入为虚拟世界创新3D对象生成

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-12-18 DOI: 10.1002/cav.70088

An Chao Tsai, Pierre Dave Victor Katuhe

引用次数: 0

Dynamic Translational Gains Manipulation for Tiny Object Interaction 微小对象交互的动态平移增益操纵

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-12-16 DOI: 10.1002/cav.70086

Jiahui Dong, Tansi Zhang, Shengyang Luo, Christos Mousas, Yingjie Chen

{"title":"Dynamic Translational Gains Manipulation for Tiny Object Interaction","authors":"Jiahui Dong, Tansi Zhang, Shengyang Luo, Christos Mousas, Yingjie Chen","doi":"10.1002/cav.70086","DOIUrl":"https://doi.org/10.1002/cav.70086","url":null,"abstract":"<p>Interacting with small objects in virtual reality (VR) can be challenging due to the physical limitations of controllers and headsets, which often lead to unintended collisions and tracking loss when devices come too close, thereby disrupting the user's immersive experience. While researchers have developed techniques like translational gain, hand remapping, and specialized interaction to address these challenges, these approaches are often task-specific or insufficient for precise, detailed interactions or observations. To address these challenges, in this paper, we introduce a novel interaction technique called dynamic translational gains manipulation (DTGM), which adjusts scaling in real-time based on the user's proximity to objects. We conducted a user study to evaluate the effectiveness of improving precision during object manipulation and understanding the subjective mental workload of the proposed DTGM technique. Our results revealed that the DTGM technique improved interaction efficiency, making it suitable for various VR applications where precision and space optimization are crucial.</p>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cav.70086","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145852629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SD-T2LM: Long-Sequence Human Motion Generation Based on Dynamic SLERP Interpolation and Dynamic Mask Mechanism SD-T2LM：基于动态SLERP插值和动态掩模机制的长序列人体运动生成

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-12-02 DOI: 10.1002/cav.70078

Fengsen Jin, Guang Li, Jianjun Li, Chongyang Ding

{"title":"SD-T2LM: Long-Sequence Human Motion Generation Based on Dynamic SLERP Interpolation and Dynamic Mask Mechanism","authors":"Fengsen Jin, Guang Li, Jianjun Li, Chongyang Ding","doi":"10.1002/cav.70078","DOIUrl":"https://doi.org/10.1002/cav.70078","url":null,"abstract":"<div>\u0000 \u0000 <p>Text-driven human motion generation aims to synthesize coherent, natural human actions from natural-language descriptions. While current techniques are effective for short sequences, they often suffer from abrupt transitions, detail loss, and temporal misalignment when extended to long sequences. We present SD-T2LM, a unified framework that couples transition optimization, detail enhancement, and temporal alignment to produce natural, detail-rich long motion sequences. First, a dynamic SLERP interpolation selects transition length conditioned on start/end pose similarity to suppress discontinuities while preserving physical plausibility. Second, a dynamic masking mechanism progressively reduces the mask ratio from 60% to 30% during training, enabling staged learning-global structure early, fine-grained details later. Third, a Temporal Flexible Alignment loss based on Soft-DTW aligns generated and ground-truth rhythms without enforcing point-wise synchrony. On the HumanML3D dataset and KIT-ML dataset, SD-T2LM showed significant improvements in FID and diversity compared to the baseline model, while reducing transition distance and jerk.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145686105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimating Torso Direction Based on a Head-Mounted Display and Its Controllers for Steering During Virtual Locomotion 虚拟运动中基于头戴式显示器及其控制器的躯干方向估计

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-11-30 DOI: 10.1002/cav.70087

Jingbo Zhao, Mengyang Ding, Zihao Guo, Mingjun Shao

{"title":"Estimating Torso Direction Based on a Head-Mounted Display and Its Controllers for Steering During Virtual Locomotion","authors":"Jingbo Zhao, Mengyang Ding, Zihao Guo, Mingjun Shao","doi":"10.1002/cav.70087","DOIUrl":"https://doi.org/10.1002/cav.70087","url":null,"abstract":"<div>\u0000 \u0000 <p>Reliable estimation of torso direction is essential for virtual locomotion as it controls the locomotion direction in virtual environments. Existing approaches rely on external sensors to track torso direction or use the poses and/or movements from the head, hands, or feet to control the direction of travel. In addition, deep learning methods based on a head-mounted display (HMD) and its controllers were proposed for torso direction estimation but are unable to produce continuous estimates or that the estimation errors were not systematically evaluated. On the other hand, 3D full-body human motion generation methods based on an HMD and its controllers are capable of estimating torso direction but this capability was largely ignored for its use in virtual steering. We proposed a new method called TCNPoser that can perform torso direction estimation and generate 3D full-body human motion. Through offline evaluation and a user study, we show that the proposed method achieves the state-of-the-art (SOTA) performance for real-time torso direction estimation.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145686401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bridging Real and Virtual: Augmented Reality as a Catalyst for Creative Learning in Beverage Preparation Courses 连接真实与虚拟：增强现实作为饮料制备课程创造性学习的催化剂

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-11-30 DOI: 10.1002/cav.70083

Yen-Cheng Chen

{"title":"Bridging Real and Virtual: Augmented Reality as a Catalyst for Creative Learning in Beverage Preparation Courses","authors":"Yen-Cheng Chen","doi":"10.1002/cav.70083","DOIUrl":"https://doi.org/10.1002/cav.70083","url":null,"abstract":"<div>\u0000 \u0000 <p>The COVID-19 pandemic has profoundly disrupted traditional face-to-face education, accelerating the shift towards digital learning environments and prompting the adoption of innovative pedagogical approaches. Among these, Augmented Reality (AR) has emerged as a transformative educational tool, offering immersive and interactive platforms that enhance students' understanding of complex concepts. This study investigates the integration of AR technology into university-level beverage preparation courses, with the aim of fostering creativity and strengthening professional competencies. The findings indicate that AR has considerable potential to enhance creative performance, reshape pedagogical practices, and promote self-directed learning. By addressing prevalent learning challenges and providing actionable insights into students' developmental progress, AR supports the design of tailored teaching strategies while cultivating industry-relevant skills. This research highlights the role of AR in advancing inclusive, equitable, and high-quality education, in alignment with Sustainable Development Goal 4 (SDG 4), and underscores its broader significance in redefining educational paradigms in the post-pandemic era.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145686400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Convergence of Deep Learning and the Metaverse: A Multidisciplinary Survey of Current Research and Future Directions 深度学习和元宇宙的融合：当前研究和未来方向的多学科调查

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-11-25 DOI: 10.1002/cav.70082

Jothi Prakash Venugopal, Arul Antran Vijay Subramanian, Gopikrishnan Sundaram, Mahendhiran Ponnambalam Devadoss

{"title":"The Convergence of Deep Learning and the Metaverse: A Multidisciplinary Survey of Current Research and Future Directions","authors":"Jothi Prakash Venugopal, Arul Antran Vijay Subramanian, Gopikrishnan Sundaram, Mahendhiran Ponnambalam Devadoss","doi":"10.1002/cav.70082","DOIUrl":"https://doi.org/10.1002/cav.70082","url":null,"abstract":"<div>\u0000 \u0000 <p>The convergence of deep learning and the Metaverse represents a pivotal frontier in the evolution of intelligent digital ecosystems. This paper presents a comprehensive survey of how deep learning techniques spanning convolutional, generative, transformer-based, and reinforcement architectures collectively enable perception, creation, cognition, and governance within immersive virtual worlds. Building upon this synthesis, we propose the Deep Learning-Empowered Metaverse Intelligence (DL-MI) framework, which unifies sensory intelligence, generative world-building, adaptive reasoning, and ethical-social governance into a cohesive architecture. The study illustrates how deep learning facilitates realistic avatar synthesis, dynamic environmental rendering, emotion-aware interaction, and predictive personalization, thereby transforming the Metaverse from reactive systems to anticipatory, self-evolving spaces. Key challenges such as data privacy, algorithmic bias, and computational sustainability are critically examined alongside emerging paradigms, including quantum-augmented AI and federated collaboration. By integrating technical, ethical, and societal dimensions, this survey provides a structured foundation for developing scalable, transparent, and human-centered Metaverse intelligence.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145626139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MotionBlend GAN: An Approach for Realistic Video Content Creation With Embedded Approach for Human Subjects MotionBlend GAN：一种用于人类主题的嵌入式方法的逼真视频内容创作方法

IF 1.7 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2025-11-25 DOI: 10.1002/cav.70085

Lalit Kumar, Dushyant Kumar Singh

{"title":"MotionBlend GAN: An Approach for Realistic Video Content Creation With Embedded Approach for Human Subjects","authors":"Lalit Kumar, Dushyant Kumar Singh","doi":"10.1002/cav.70085","DOIUrl":"https://doi.org/10.1002/cav.70085","url":null,"abstract":"<div>\u0000 \u0000 <p>The proposed MotionBlend GAN model marks a significant step forward in video synthesis by blending the motion from a source video with the appearance of a target person's image. As training progresses, the model improves video creation by enhancing the smoothness and natural flow of motion, resulting in more coherent and lifelike videos. Using advanced techniques like MoBConv blocks of EfficientNet-B7, OpenPose for precise pose detection, ResNet blocks for feature integration, and a 3D CNN discriminator, the model produces high-quality videos that maintain both spatial and temporal consistency. After 200 epochs, the model achieved an adversarial loss of 0.2265, with metrics like PSNR at 20.246, SSIM at 0.867, and LPIPS at 0.178. The high PSNR and SSIM values, along with the low LPIPS, show that the generated frames are well aligned and preserve important details. These results highlight the model's strong performance over time, consistently generating visually convincing videos of human activities using a reference image and source video. The model effectively transfers motion from video to image, creating realistic videos of human activity in comparison to existing models.</p>\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"36 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145626137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0