从像素到肖像：会说话头像生成技术与应用的全面综述
From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications
AI总结：
综述会说话头像生成技术，将文献分为四类方法并讨论其技术思想等。分析定量指标与感知质量差距，比较公开模型，研究新兴趋势，确定开放挑战，为从业者提供领域地图，突出相关技术和社会问题。
摘要：
会说话头像生成已从基于地标和GAN的面部动画迅速发展到扩散模型、神经渲染、3D感知头像和基础模型辅助系统。这一进展使音频、图像和视频驱动的会说话头像越来越逼真，但该领域也变得难以梳理，因为方法在输入、假设、可控性、时间稳定性、计算成本和滥用风险等方面存在很大差异。本综述批判性地回顾了会说话头像生成技术，将文献分为图像驱动、音频驱动、视频驱动和基于3D/神经渲染的四大类方法。对于每一类，我们讨论了潜在的技术思想、代表性方法、优势、局限性、数据集和评估实践。除了编目先前的工作，我们分析了常见定量指标与感知质量之间的持续差距，并在推理时间、内存需求和人工评级的视觉质量方面比较了公开可用的模型。我们还研究了新兴趋势，包括基于扩散的生成、3D感知表示学习、可控情感表达、实时部署以及溯源、水印和深度伪造检测的重要性日益增加。最后，我们确定了围绕稳健评估、身份保留、唇同步、时间一致性、人口统计公平性、计算效率和负责任使用的开放挑战。本综述旨在为研究人员和从业者提供会说话头像生成领域的结构化和最新地图，同时突出应塑造未来工作的技术和社会问题。
英文摘要：
Talking head generation has progressed rapidly from landmark- and GAN-based facial animation to diffusion models, neural rendering, 3D-aware avatars, and foundation-model-assisted systems. This progress has enabled increasingly realistic audio-, image-, and video-driven talking heads, but it has also made the field difficult to navigate because methods differ substantially in their inputs, assumptions, controllability, temporal stability, computational cost, and risks of misuse. This survey provides a critical review of talking head generation techniques, organizing the literature into four broad families: image-driven, audio-driven, video-driven, and 3D/neural-rendering-based approaches. For each family, we discuss the underlying technical ideas, representative methods, strengths, limitations, datasets, and evaluation practices. Beyond cataloguing prior work, we analyse the persistent gap between commonly reported quantitative metrics and perceptual quality, and compare publicly available models in terms of inference time, memory requirements, and human-rated visual quality. We also examine emerging trends, including diffusion-based generation, 3D-aware representation learning, controllable emotional expression, real-time deployment, and the growing importance of provenance, watermarking, and deepfake detection. Finally, we identify open challenges around robust evaluation, identity preservation, lip synchronisation, temporal consistency, demographic fairness, computational efficiency, and responsible use. This review aims to provide researchers and practitioners with a structured and up-to-date map of the talking head generation landscape, while highlighting the technical and societal questions that should shape future work.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
