Zhuoran Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhuoran Zhao has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Angela Yao
National University of Singapore, Singapore, Singapore
2 shared publications Debang Wang
Dept. of Computer Science School of Computing National University of Singapore
2 shared publicationsDelong Chen
Xiaobing.AI
2 shared publications- Jiayin Zhu
National University of Singapore
2 shared publications - Jinbin Bai
National University of Singapore
2 shared publications - Linlin Yang
Communication University of China
2 shared publications
Latest Publications
- 8 March 2024
- Published by Springer Nature
- p. 115-130
HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
- 8 March 2024
- Published by Springer Nature
- p. 115-130
HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
- Open Access
Taming Diffusion Models for Music-driven Conducting Motion Generation
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior works have applied Generative Adversarial Networks (GAN) to this task, but the promising diffusion model, which recently showed its advantages in terms of both training stability and output quality, has not been exploited in this context. This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation, which integrates the diffusion model to a two-stage learning framework. We further propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations and increase motion diversity. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion. Experimental results demonstrate the advantages of our model.
Open AccessTaming Diffusion Models for Music-driven Conducting Motion Generation
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior works have applied Generative Adversarial Networks (GAN) to this task, but the promising diffusion model, which recently showed its advantages in terms of both training stability and output quality, has not been exploited in this context. This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation, which integrates the diffusion model to a two-stage learning framework. We further propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations and increase motion diversity. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion. Experimental results demonstrate the advantages of our model.
- Open Access
- 3 October 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 1 (1) , 40-44
Taming Diffusion Models for Music-Driven Conducting Motion Generation
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior works have applied Generative Adversarial Networks (GAN) to this task, but the promising diffusion model, which recently showed its advantages in terms of both training stability and output quality, has not been exploited in this context. This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation, which integrates the diffusion model to a two-stage learning framework. We further propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations and increase motion diversity. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion. Experimental results demonstrate the advantages of our model. The code is released at https://github.com/viiika/Diffusion-Conductor.
- 3 October 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 1 (1) , 40-44
Open AccessTaming Diffusion Models for Music-Driven Conducting Motion Generation
Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior works have applied Generative Adversarial Networks (GAN) to this task, but the promising diffusion model, which recently showed its advantages in terms of both training stability and output quality, has not been exploited in this context. This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation, which integrates the diffusion model to a two-stage learning framework. We further propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations and increase motion diversity. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion. Experimental results demonstrate the advantages of our model. The code is released at https://github.com/viiika/Diffusion-Conductor.
- Open Access
HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D hand meshes while recovering realistic textures. Our method achieves superior texture reconstruction by employing a parametric hand model with predefined texture assets, and by establishing a texture reconstruction consistency between the rendered and input images during training. Moreover, based on pretraining the network on an annotated dataset, we apply varying degrees of supervision using our pipeline, i.e., self-supervision, weak supervision, and full supervision, and discuss the various levels of contributions of the learned high-fidelity textures in enhancing hand pose and shape estimation. Experimental results on public benchmarks including FreiHAND and HO-3D demonstrate that our method outperforms the state-of-the-art hand reconstruction methods in texture reconstruction quality while maintaining comparable accuracy in pose and shape estimation. Our code is available at https://github.com/viridityzhu/HiFiHR.
Open AccessHiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D hand meshes while recovering realistic textures. Our method achieves superior texture reconstruction by employing a parametric hand model with predefined texture assets, and by establishing a texture reconstruction consistency between the rendered and input images during training. Moreover, based on pretraining the network on an annotated dataset, we apply varying degrees of supervision using our pipeline, i.e., self-supervision, weak supervision, and full supervision, and discuss the various levels of contributions of the learned high-fidelity textures in enhancing hand pose and shape estimation. Experimental results on public benchmarks including FreiHAND and HO-3D demonstrate that our method outperforms the state-of-the-art hand reconstruction methods in texture reconstruction quality while maintaining comparable accuracy in pose and shape estimation. Our code is available at https://github.com/viridityzhu/HiFiHR.