Baihui Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Baihui Tang has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Sanxing Cao
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
2 shared publications - Dong Wang
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
1 shared publication
Latest Publications
- Open Access
- 13 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4840
Let Toon Talk: Speech-Driven 3D Cartoon Animation via Parametric Modeling and Flow Matching
Speech-driven 3D cartoon facial animation remains underexplored due to the difficulty of handling heterogeneous geometries with exaggerated proportions, limited generalization to diverse unseen subjects, and the scarcity of datasets. To address these challenges, we propose Let Toon Talk, a two-stage cascaded framework that effectively mitigates these bottlenecks in both modeling and driving. It enables one-shot, speech-synchronized 3D animation from a single unseen humanoid cartoon image, driven by arbitrary audio. Specifically, for avatar modeling, we propose a parametric adaptation mechanism to capture diverse heterogeneous facial topologies, which subsequently guides a feed-forward reconstruction module to create high-quality 3D Gaussian Splatting (3DGS) avatars. Building upon this, for speech driving, we introduce an Identity-Adaptive Flow Matching network. This generative module effectively maps audio to precise facial dynamics, achieving identity-adaptive motion synthesis for diverse humanoid cartoon characters without per-subject pretraining. Furthermore, we construct a hybrid cartoon talking-face dataset with a systematic curation strategy to bridge the data gap. Extensive experiments demonstrate that our framework produces high-quality, temporally coherent animations, exhibiting effective generalization on unseen structurally humanoid cartoon characters.
- 13 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4840
Open AccessLet Toon Talk: Speech-Driven 3D Cartoon Animation via Parametric Modeling and Flow Matching
Speech-driven 3D cartoon facial animation remains underexplored due to the difficulty of handling heterogeneous geometries with exaggerated proportions, limited generalization to diverse unseen subjects, and the scarcity of datasets. To address these challenges, we propose Let Toon Talk, a two-stage cascaded framework that effectively mitigates these bottlenecks in both modeling and driving. It enables one-shot, speech-synchronized 3D animation from a single unseen humanoid cartoon image, driven by arbitrary audio. Specifically, for avatar modeling, we propose a parametric adaptation mechanism to capture diverse heterogeneous facial topologies, which subsequently guides a feed-forward reconstruction module to create high-quality 3D Gaussian Splatting (3DGS) avatars. Building upon this, for speech driving, we introduce an Identity-Adaptive Flow Matching network. This generative module effectively maps audio to precise facial dynamics, achieving identity-adaptive motion synthesis for diverse humanoid cartoon characters without per-subject pretraining. Furthermore, we construct a hybrid cartoon talking-face dataset with a systematic curation strategy to bridge the data gap. Extensive experiments demonstrate that our framework produces high-quality, temporally coherent animations, exhibiting effective generalization on unseen structurally humanoid cartoon characters.
- Open Access
- 18 June 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (12) , 6843
Research on Weakly Supervised Face Segmentation Technology Based on Visual Large Models in New Media Post-Production
Face segmentation is a critical component in new media post-production, enabling the precise separation of facial regions from complex backgrounds at the pixel level. With the increasing demand for flexible and efficient segmentation solutions across diverse media scenarios—such as variety shows, period dramas, and other productions—there is a pressing need for adaptable methods that can perform reliably under varying conditions. However, existing approaches primarily depend on fully supervised learning, which requires extensive manual annotation and incurs high labor costs. To overcome these limitations, we propose a novel weakly supervised face segmentation framework that leverages large-scale vision models to automatically generate high-quality pseudo-labels. These pseudo-labels are then used to train segmentation networks in a dual-model architecture, where two complementary models collaboratively enhance segmentation performance. Our method significantly reduces the reliance on manual labeling while maintaining competitive accuracy. Extensive experiments demonstrate that our approach not only improves segmentation precision and efficiency but also streamlines post-production workflows, lowering human effort and accelerating project timelines. Furthermore, this framework reduced reliance on annotations in the field of weakly supervised learning for facial image processing in the new media post-production scenario.
- 18 June 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (12) , 6843
Open AccessResearch on Weakly Supervised Face Segmentation Technology Based on Visual Large Models in New Media Post-Production
Face segmentation is a critical component in new media post-production, enabling the precise separation of facial regions from complex backgrounds at the pixel level. With the increasing demand for flexible and efficient segmentation solutions across diverse media scenarios—such as variety shows, period dramas, and other productions—there is a pressing need for adaptable methods that can perform reliably under varying conditions. However, existing approaches primarily depend on fully supervised learning, which requires extensive manual annotation and incurs high labor costs. To overcome these limitations, we propose a novel weakly supervised face segmentation framework that leverages large-scale vision models to automatically generate high-quality pseudo-labels. These pseudo-labels are then used to train segmentation networks in a dual-model architecture, where two complementary models collaboratively enhance segmentation performance. Our method significantly reduces the reliance on manual labeling while maintaining competitive accuracy. Extensive experiments demonstrate that our approach not only improves segmentation precision and efficiency but also streamlines post-production workflows, lowering human effort and accelerating project timelines. Furthermore, this framework reduced reliance on annotations in the field of weakly supervised learning for facial image processing in the new media post-production scenario.