A Survey of Talking Head Synthesis Techniques: Portrait Generation, Driving Mechanisms, and Editing
ACM Computing Surveys · 2026-05-31 · 58 (7) · 1-43
DOI: 10.1145/3785656 ↗At a glance
Journal article in ACM Computing Surveys, published online on 2026-02-03. Written by Ming Meng and 6 co-authors. Cited 2 times so far (Crossref); 235 references. Funded by: Postdoctoral Fellowship Program and China Postdoctoral Science Foundation, Beijing Natural Science Foundation, Fundamental Research Funds for the Central Universities.
Abstract (original language)
Talking head synthesis, an advanced method for generating portrait videos from a still image driven by specific content, has garnered widespread attention in virtual reality, augmented reality and game production. Recently, significant breakthroughs have been made with the introduction of novel models such as the transformer and the diffusion model. Current methods can not only generate new content but also edit the generated material. This survey systematically reviews the technology, categorizing it into three pivotal domains: portrait generation, driving mechanisms, and editing techniques. We summarize milestone studies and critically analyze their innovations and shortcomings within each domain. Additionally, we organize an extensive collection of datasets and provide a thorough performance analysis of current methodologies based on various evaluation metrics, aiming to furnish a clear framework and robust data support for future research. Finally, we explore application scenarios of talking head synthesis, illustrate them with specific cases, and examine potential future directions. Moreover, we present a first‐of‐its‐kind system‐level analysis of integration‐specific challenges—such as identity consistency drift, interface incompatibility, and real‐time synchronization—that emerge only when portrait generation, driving, and editing are jointly deployed.
Funding
- Postdoctoral Fellowship Program and China Postdoctoral Science Foundation
- Beijing Natural Science Foundation
- Fundamental Research Funds for the Central Universities
- Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing
Cite
APA
Meng, M., Zhao, Y., Zhang, B., Zhu, Y., Shi, W., Wen, M., & Fan, Z. (2026). A Survey of Talking Head Synthesis Techniques: Portrait Generation, Driving Mechanisms, and Editing. ACM Computing Surveys, 58(7), 1-43. https://doi.org/10.1145/3785656
Vancouver
Meng M, Zhao Y, Zhang B, Zhu Y, Shi W, Wen M, et al. A Survey of Talking Head Synthesis Techniques: Portrait Generation, Driving Mechanisms, and Editing. ACM Computing Surveys. 2026;58(7):1-43. doi:10.1145/3785656
BibTeX
@article{Meng2026,
author = {Meng, Ming and Zhao, Yufei and Zhang, Bo and Zhu, Yonggui and Shi, Weimin and Wen, Maxwell and Fan, Zhaoxin},
title = {A Survey of Talking Head Synthesis Techniques: Portrait Generation, Driving Mechanisms, and Editing},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {7},
pages = {1--43},
doi = {10.1145/3785656}
}
EUVIMED