{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:23:07Z","timestamp":1779189787429,"version":"3.51.4"},"reference-count":35,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T00:00:00Z","timestamp":1742256000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the field of talking face generation, two-stage audio-based generation methods have attracted significant research interest. However, these methods still face challenges in achieving lip\u2013audio synchronization during face generation, as well as issues with the discontinuity between the generated parts and original face in rendered videos. To overcome these challenges, this paper proposes a two-stage talking face generation method. The first stage is the landmark generation stage. A dynamic convolutional transformer generator is designed to capture complex facial movements. A dual-pipeline parallel processing mechanism is adopted to enhance the temporal feature correlation of input features and the ability to model details at the spatial scale. In the second stage, a dynamic Gaussian renderer (adaptive Gaussian renderer) is designed to realize seamless and natural connection of the upper- and lower-boundary areas through a Gaussian blur masking technique. We conducted quantitative analyses on the LRS2, HDTF, and MEAD neutral expression datasets. Experimental results demonstrate that, compared with existing methods, our approach significantly improves the realism and lip\u2013audio synchronization of talking face videos. In particular, on the LRS2 dataset, the lip\u2013audio synchronization rate was improved by 18.16% and the peak signal-to-noise ratio was improved by 12.11% compared to state-of-the-art works.<\/jats:p>","DOI":"10.3390\/s25061885","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T10:43:51Z","timestamp":1742294631000},"page":"1885","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Continuous Talking Face Generation Based on Gaussian Blur and Dynamic Convolution"],"prefix":"10.3390","volume":"25","author":[{"given":"Ying","family":"Tang","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazhi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6508-2308","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"102558","DOI":"10.1016\/j.displa.2023.102558","article-title":"Talking face generation driven by time-frequency domain features of speech audio","volume":"80","author":"Zhang","year":"2023","journal-title":"Displays"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tan, S., Ji, B., and Pan, Y. (2023, January 2\u20136). EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1007\/s11263-019-01150-y","article-title":"You Said That? Synthesising Talking Faces from Audio","volume":"127","author":"Jamaludin","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., and Jawahar, C.V. (2020, January 12\u201316). A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413532"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., and Tong, X. (2019, January 16\u201320). Accurate 3D Face Reconstruction With Weakly-Supervised Learning: From Single Image to Image Set. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/TVCG.2024.3371064","article-title":"Pose-Aware 3D Talking Face Synthesis using Geometry-guided Audio-Vertices Attention","volume":"31","author":"Li","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing Obama","volume":"36","author":"Suwajanakorn","year":"2017","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhong, W., Fang, C., Cai, Y., Wei, P., Zhao, G., Lin, L., and Li, G. (2023, January 18\u201322). Identity-Preserving Talking Face Generation with Landmark and Appearance Priors. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhao, Y., Liu, L., Xu, T., Li, Q., and Li, S. (2023). Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks. arXiv.","DOI":"10.21437\/Interspeech.2023-749"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hu, Z., Deng, W., Fan, C., Lv, T., and Ding, Y. (2023, January 7\u201314). DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., and Xu, C. (2019, January 16\u201320). Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, Z., Maddox, R.K., Duan, Z., and Xu, C. (2018, January 8\u201314). Lip Movements Generation at a Glance. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref_13","unstructured":"Chung, J.S., and Zisserman, A. (2016, January 20\u201324). Lip Reading in the Wild. Proceedings of the Asian Conference on Computer Vision, Taipei, Taiwan."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, S., Yu, W., Gao, B., Li, C., and Wang, T. (2025). Accurate Real-Time Live Face Detection Using Snapshot Spectral Imaging Method. Sensors, 25.","DOI":"10.3390\/s25030952"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"O\u2019Shaughnessy, D. (2025). Speaker Diarization: A Review of Objectives and Methods. Appl. Sci., 15.","DOI":"10.3390\/app15042002"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ko, S. (2025). Analog Gaussian-Shaped Filter Design and Current Mode Compensation for Dot-Matrix TSP Readout Systems. Appl. Sci., 15.","DOI":"10.3390\/app15041845"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wu, X., Hirota, K., Dai, Y., and Shao, S. (2025). Dynamic Multi-Population Mutation Architecture-Based Equilibrium Optimizer and Its Engineering Application. Appl. Sci., 15.","DOI":"10.3390\/app15041795"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ravichandran, N., Bidorn, B., Mercan, O., and Paneerselvam, B. (2025). Data-Driven Machine-Learning-Based Seismic Response Prediction and Damage Classification for an Unreinforced Masonry Building. Appl. Sci., 15.","DOI":"10.3390\/app15041686"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"104724","DOI":"10.1016\/j.dsp.2024.104724","article-title":"Gaussian second derivative blur kernels for image deblurring","volume":"155","author":"Huang","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Alghamdi, M.M., Wang, H., Bulpitt, A.J., and Hogg, D.C. (2022, January 10\u201314). Talking Head from Speech Audio using a Pre-trained Image Generator. Proceedings of the 30th ACM International Conference on Multimedia, Lisbon, Portugal.","DOI":"10.1145\/3503161.3548101"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104911","DOI":"10.1016\/j.imavis.2024.104911","article-title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","volume":"142","author":"Bigioi","year":"2023","journal-title":"Image Vis. Comput."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.1109\/TPAMI.2023.3339964","article-title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","volume":"46","author":"Hong","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, X., Xu, Y., Wu, Q., Zhou, H., Wu, W., and Zhou, B. (2022, January 23\u201327). Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref_24","first-page":"1","article-title":"MakeItTalk: Speaker-Aware Talking Head Animation","volume":"39","author":"Zhou","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rochow, A., Schwarz, M., and Behnke, S. (2024). FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features. arXiv.","DOI":"10.1109\/CVPR52733.2024.00737"},{"key":"ref_26","unstructured":"Ma, Y., Zhang, S., Wang, J., Wang, X., Zhang, Y., and Deng, Z. (2023). DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Model. arXiv."},{"key":"ref_27","unstructured":"Yi, R., Ye, Z., Zhang, J., Bao, H., and Liu, Y.J. (2020). Audio-driven Talking Face Video Generation with Natural Head Pose. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1109\/TIFS.2022.3146783","article-title":"Everybody\u2019s Talkin\u2019: Let Me Talk as You Want. IEEE Trans","volume":"17","author":"Song","year":"2020","journal-title":"Inf. Forensics Secur."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ji, X., Zhou, H., Wang, K., Wu, Q., Wu, W., Xu, F., and Cao, X. (2022, January 8\u201311). EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model. Proceedings of the ACM SIGGRAPH 2022 Conference Proceedings, Virtual Event.","DOI":"10.1145\/3528233.3530745"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., He, W., Li, M., Tian, K., Zhang, Z., Cheng, J., Wang, Y., and Liao, J. (2022, January 22\u201327). Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition. Proceedings of the ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.","DOI":"10.1109\/ICASSP43922.2022.9747284"},{"key":"ref_31","first-page":"572","article-title":"Speech-driven video generation of speaking faces based on keypoint representation","volume":"034","author":"Nian","year":"2021","journal-title":"Pattern Recognit. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, L., Cui, G., Liu, C., Li, Z., Kou, Z., Xu, Y., and Xu, C. (2020, January 23\u201328). Talking-head Generation with Rhythmic Head Motion. Proceedings of the European Conference on Computer Vision, Glasgow, Scotland.","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref_33","unstructured":"Lou, M., Zhou, H.Y., Yang, S., and Yu, Y. (2023). TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tian, Y. (2022). Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers. arXiv.","DOI":"10.2139\/ssrn.4354042"},{"key":"ref_35","unstructured":"Tan, S., Ji, B., Bi, M., and Pan, Y. (October, January 28). EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis. Proceedings of the European Conference on Computer Vision, Milan, Italy."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1885\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:56:02Z","timestamp":1760028962000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,18]]},"references-count":35,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["s25061885"],"URL":"https:\/\/doi.org\/10.3390\/s25061885","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,18]]}}}