HeadGAN: One-shot Neural Head Synthesis and Editing
Open accessAbstract
Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results. However, most of them either perform poorly in terms of photo-realism, or fail to meet the identity preservation problem, or do not fully transfer the driving pose and expression. We propose HeadGAN, a novel system that conditions synthesis on 3D face representations, which can be extracted from any driving video and adapted to the facial geometry of any reference image, disentangling identity from expression. We further improve mouth movements, by utilising audio features as a complementary input. The 3D face representation enables HeadGAN to be further used as an efficient method for compression and reconstruction and a tool for expression and pose editing.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Pioneer talking-head generation works typically utilize biometric signals such as facial keypoints or 3D priors as intermediate motion representation to animate the reference face while ensuring lip synchronization.
“pioneer talking-head generation works typically utilize biometric signals such as facial keypoints [22, 28, 30, 45], or 3D priors [11, 13, 16, 23, 32, 43, 44] as intermediate motion representation to animate the reference face while ensuring lip synchronization.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [11]
Cites
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696 · see citing works
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · see citing works
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365 · see citing works
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781 · see citing works
Self-citationVoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256 · see citing works
VoxCeleb: A Large-Scale Speaker Identification Dataset
Nagrani, A., Chung, J. S., & Zisserman, A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-950 · Cited by 2,210 · see citing works
Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Liu, G., Tao, A., Kautz, J., & Catanzaro, B. (2018) · arXiv · doi:10.48550/arxiv.1808.06601 · Cited by 594 · see citing works
Chung, J. S., & Zisserman, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54184-6_6 · Cited by 537 · see citing works
Combining Residual Networks with LSTMs for Lipreading
Stafylakis, T., & Tzimiropoulos, G. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-85 · Cited by 348 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Zhang, W., Cun, X., Wang, X., Zhang, Y., Shen, X., Guo, Y., Shan, Y., & Wang, F. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00836 · Cited by 336 · see citing works
MoCha: Towards Movie-Grade Talking Character Synthesis
Wei, C., Sun, B., Ma, H., Hou, J., Juefei-Xu, F., He, Z., Dai, X., Zhang, L., Li, K., Hou, T., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.23307
“…audio sequence and a reference face, pioneer talking-head generation works typically utilize biometric signals such as facial keypoints [22, 28, 30, 45], or 3D priors [11, 13, 16, 23, 32, 43, 44] as intermediate motion representation to animate the reference face while ensuring lip synchronization.”
- Authors
- Doukas, M. C., Zafeiriou, S., & Sharmanska, V.
- Affiliations
- Imperial College London (GB)
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 14378-14387
- OpenAlex
- W3140912147
- Cited by
- 117
- References
- 9
- Citations by year
- 2026: 10 · 2025: 36 · 2024: 25 · 2023: 37 · 2022: 9
- FWCI
- 5.81
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Sussex Research Online (University of Sussex) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Keywords
- facial expression editing, identity preservation, driving video, facial reconstruction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
