The DOI matches its Crossref record; 48 of the 50 references it cites were found in a registry or an index.
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Open accessAbstract
Generating talking head videos through a face image and a piece of speech audio still contains many challenges. i.e., unnatural head movement, distorted expression, and identity modification. We argue that these issues are mainly caused by learning from the coupled 2D motion fields. On the other hand, explicitly using 3D information also suffers problems of stiff expression and incoherent video. We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation. To learn the realistic motion coefficients, we explicitly model the connections between audio and different types of motion coefficients individually. Precisely, we present ExpNet to learn the accurate facial expression from audio by distilling both coefficients and 3D-rendered faces. As for the head pose, we design PoseVAE via a conditional VAE to synthesize head motion in different styles. Finally, the generated 3D motion coefficients are mapped to the unsupervised 3D keypoints space of the proposed face render to synthesize the final video. We conducted extensive experiments to demonstrate the superiority of our method in terms of motion and video quality.11The code and demo videos are available at https://sadtalker.github.io.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The cited source says what the claim attributes to it.
In the citing paper
“SadTalker [44] first extracts 3DMM coefficients from audio and then renders the face in a 3D-aware manner.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [44]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
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
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
A morphable model for the synthesis of 3D faces
Blanz, V., & Vetter, T. R. (1999) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/311535.311556 · Cited by 4,695
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 1×
“Both visible and invisible video watermarks will be inserted into the produced video for generated content identification similar to Dall-E [30] and Imagen [32].”
MethodVoxCeleb: 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
Tutorial on Variational Autoencoders
Doersch, C. (2016) · arXiv · doi:10.48550/arxiv.1606.05908 · Cited by 1,470
A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild
Prajwal, K. R., Mukhopadhyay, R., Namboodiri, V. P., & Jawahar, C. V. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413532 · Cited by 897
Research works printed but not linked: 3
- kingma, 2014, A method for stochastic optimization, ArXiv Preprint
- seitzer, 2020, pytorch-fid FID Score for PyTorch
- li, 0, Bailando: 3d dance generation via actor-critic gpt with choreographic memory, CVPR
Cited by
Sorted by citations
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M., & Shan, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00825 · Cited by 233
Self-citationEvalCrafter: Benchmarking and Evaluating Large Video Generation Models
Liu, Y., Cun, X., Liu, X., Wang, X., Zhang, Y., Chen, H., Liu, Y., Zeng, T., Chan, R., & Shan, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02090 · Cited by 219
Self-citationTian, L., Wang, Q. J., Zhang, B., & Bo, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73010-8_15 · Cited by 211
Tian, L., Wang, Q., Zhang, B., & Bo, L. (2024) · arXiv · doi:10.48550/arxiv.2402.17485 · Cited by 92
Sun, Z., Lv, T. S., Ye, S., Lin, M. G., Sheng, J., Wen, Y., Yu, M., & Liu, Y. (2024) · ACM Transactions on Graphics · doi:10.1145/3658221 · Cited by 98
Metadata
- Authors
- Zhang, W., Cun, X., Wang, X., Zhang, Y., Shen, X., Guo, Y., Shan, Y., & Wang, F.
- Affiliations
- Xi'an Jiaotong University (CN)
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence
- Ant Group (China) (CN)
- Tencent (China) (CN)
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 8652-8661
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386072021
- Cited by
- 336
- References
- 50
- Citations by year
- 2026: 86 · 2025: 131 · 2024: 105 · 2023: 14
- FWCI
- 35.93
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2022YFB3303800)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- talking head generation, audio-driven face animation, facial expression synthesis, stylized animation
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
