让动漫风格角色开口说话时能自然比划和变脸
Co-Speech Gesture and Facial Expression Generation for Non-Photorealistic 3D Characters
- 从漫画和对话语义中提取表情数据驱动生成
- 用户测试显示在多维度上优于现有方法
- 适合动画、游戏等非写实角色的表达生成
随着对话式AI的发展，身体表达（包括手势和面部表情）的研究也取得进展。然而，多数现有研究聚焦于写实虚拟形象，难以适用于动漫等非写实角色。本文提出基于漫画中提取的表情数据及对话语义特定手势的方法，实现非写实角色的情感表达，包含动漫特有的夸张表现。用户研究表明，该方法在多个评估维度上均显著优于现有技术。
原文摘要 · Abstract (English)
With the advancement of conversational AI, research on bodily expressions, including gestures and facial expressions, has also progressed. However, many existing studies focus on photorealistic avatars, making them unsuitable for non-photorealistic characters, such as those found in anime. This study proposes methods for expressing emotions, including exaggerated expressions unique to non-photorealistic characters, by utilizing expression data extracted from comics and dialogue-specific semantic gestures. A user study demonstrated significant improvements across multiple aspects when compared to existing research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。