Ziqiao Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ziqiao Peng has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Hongyan Liu
Tsinghua University, Beijing, China
5 shared publications - Jun He
Renmin University of China, Beijing, China
5 shared publications - Kaixing Yang
Renmin University of China, Beijing, China
4 shared publications - Puwei Wang
Renmin University of China, Beijing, China
4 shared publications - Xiangyue Zhang
Wuhan University, Wuhan, China
4 shared publications - Xulong Tang
Malou Tech Inc
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-74
MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-74
Open AccessMATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation
- 2 October 2026
- Published by Springer Nature
- p. 56-74
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
- 2 October 2026
- Published by Springer Nature
- p. 56-74
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
- 10 September 2026
- Published by Springer Nature
- p. 571-588
OmniDance: Multimodal Driven Dance Video Generation with Large-Scale Internet Data
- 10 September 2026
- Published by Springer Nature
- p. 571-588
OmniDance: Multimodal Driven Dance Video Generation with Large-Scale Internet Data
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessMACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
- 1 January 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Artificial Intelligence and Robotics Research
- Vol. 02
Morpheus: A Neural-Driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control
Previous animatronic faces struggle to express emotions effectively due to hardware and software limitations. On the hardware side, earlier approaches either used rigid-driven mechanisms, which provided precise control but were difficult to design within constrained spaces, or tendon-driven mechanisms, which are more space-efficient but challenging to control. In contrast, we propose a hybrid actuation approach that combines the best of both worlds. The eyes and mouth– key areas for emotional expression — are controlled using rigid mechanisms for precise movement, while the nose and cheek, which convey subtle facial microexpressions, are driven by strings. This design allows us to build a compact yet versatile hardware platform capable of expressing a wide range of emotions. On the algorithmic side, our method introduces a self-modeling network that maps motor actions to facial landmarks, allowing us to automatically establish the relationship between blendshape coefficients for different facial expressions and the corresponding motor control signals through gradient backpropagation. We then train a neural network to map speech input to corresponding blendshape controls. With our method, we can generate distinct emotional expressions such as happiness, fear, disgust, and anger, from any given sentence, each with nuanced, emotion-specific control signals — a feature that has not been demonstrated in earlier systems. We release the hardware design and code at https://github.com/ZZongzheng0918/Morpheus-Hardware and https://github.com/ZZongzheng0918/Morpheus-Software .
- 1 January 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Artificial Intelligence and Robotics Research
- Vol. 02
Morpheus: A Neural-Driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control
Previous animatronic faces struggle to express emotions effectively due to hardware and software limitations. On the hardware side, earlier approaches either used rigid-driven mechanisms, which provided precise control but were difficult to design within constrained spaces, or tendon-driven mechanisms, which are more space-efficient but challenging to control. In contrast, we propose a hybrid actuation approach that combines the best of both worlds. The eyes and mouth– key areas for emotional expression — are controlled using rigid mechanisms for precise movement, while the nose and cheek, which convey subtle facial microexpressions, are driven by strings. This design allows us to build a compact yet versatile hardware platform capable of expressing a wide range of emotions. On the algorithmic side, our method introduces a self-modeling network that maps motor actions to facial landmarks, allowing us to automatically establish the relationship between blendshape coefficients for different facial expressions and the corresponding motor control signals through gradient backpropagation. We then train a neural network to map speech input to corresponding blendshape controls. With our method, we can generate distinct emotional expressions such as happiness, fear, disgust, and anger, from any given sentence, each with nuanced, emotion-specific control signals — a feature that has not been demonstrated in earlier systems. We release the hardware design and code at https://github.com/ZZongzheng0918/Morpheus-Hardware and https://github.com/ZZongzheng0918/Morpheus-Software .
- Top Cited PapersOpen Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5292-5301
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
Speech-driven 3D face animation technique, extending its applications to various multimedia fields.Previous research has generated promising realistic lip movements and facial expressions from audio signals. However, traditional regression models solely driven by data face several essential problems, such as difficulties in accessing precise labels and domain gaps between different modalities, leading to unsatisfactory results lacking precision and coherence.To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces. The framework constructs a network system consisting of three modules: facial animator, speech recognizer, and lip-reading interpreter. The core of SelfTalk is a commutative training diagram that facilitates compatible features exchange among audio, text, and lip shape, enabling our models to learn the intricate connection between these factors. The proposed framework leverages the knowledge learned from the lip-reading interpreter to generate more plausible lip shapes. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. We recommend watching the supplementary video.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5292-5301
Top Cited PapersOpen AccessSelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
Speech-driven 3D face animation technique, extending its applications to various multimedia fields.Previous research has generated promising realistic lip movements and facial expressions from audio signals. However, traditional regression models solely driven by data face several essential problems, such as difficulties in accessing precise labels and domain gaps between different modalities, leading to unsatisfactory results lacking precision and coherence.To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces. The framework constructs a network system consisting of three modules: facial animator, speech recognizer, and lip-reading interpreter. The core of SelfTalk is a commutative training diagram that facilitates compatible features exchange among audio, text, and lip shape, enabling our models to learn the intricate connection between these factors. The proposed framework leverages the knowledge learned from the lip-reading interpreter to generate more plausible lip shapes. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. We recommend watching the supplementary video.