Yuhao Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuhao Cheng has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Yichao Yan
Shanghai Jiao Tong University
10 shared publications - Xiaokang Yang
Shanghai Jiao Tong University
6 shared publications - Zhuo Chen
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
3 shared publications - Di Xu
Huawei Technologies Company Ltd
2 shared publications Jianyu Wang
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
2 shared publications- Lincheng Li
NetEase Fuxi AI Lab, Hangzhou, China
2 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 6144-6157
Relightable and Animatable Gaussian Head Avatar From Monocular Videos
In the realm of virtual avatar creation, accurate relighting capabilities are key to enhancing realism and immersion. We propose a novel pipeline for building personalized and relightable avatars from a monocular video captured under unknown lighting. This minimal input poses challenges in material entanglement and novel-view inconsistency. To tackle these, we introduce a disentangled dynamic 3D Gaussian representation that models diverse material properties and supports photorealistic rendering and animation via a parametric face model. To resolve material ambiguity under uncontrolled lighting, we train a 2D diffusion-based model to predict canonical-lighting images and physically-based material maps from casually lit portraits. These predictions serve as supervisory signals to guide the 3D disentanglement process. Additionally, we incorporate a 3D prior to enhance novel-view consistency, improving geometry and appearance in unseen views. Experiments demonstrate that our approach significantly boosts reconstruction quality and relighting fidelity, offering a practical and cost-effective solution for creating high-quality personalized avatars.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32  (7) , 6144-6157
Relightable and Animatable Gaussian Head Avatar From Monocular Videos
In the realm of virtual avatar creation, accurate relighting capabilities are key to enhancing realism and immersion. We propose a novel pipeline for building personalized and relightable avatars from a monocular video captured under unknown lighting. This minimal input poses challenges in material entanglement and novel-view inconsistency. To tackle these, we introduce a disentangled dynamic 3D Gaussian representation that models diverse material properties and supports photorealistic rendering and animation via a parametric face model. To resolve material ambiguity under uncontrolled lighting, we train a 2D diffusion-based model to predict canonical-lighting images and physically-based material maps from casually lit portraits. These predictions serve as supervisory signals to guide the 3D disentanglement process. Additionally, we incorporate a 3D prior to enhance novel-view consistency, improving geometry and appearance in unseen views. Experiments demonstrate that our approach significantly boosts reconstruction quality and relighting fidelity, offering a practical and cost-effective solution for creating high-quality personalized avatars.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP  (15209210) , 1-13
ExpDiff: Generating High-Fidelity 3D Facial Expression Meshes and BRDF Textures Via Diffusion Model
3D face generation is a critical task for immersive multimedia applications, where a key challenge is the joint synthesis of expressive geometry and BRDF textures. Existing methods often struggle with geometric-textural coherence and corresponding reflectance modeling. To overcome these limitations, we present ExpDiff, a framework that generates expression meshes and corresponding BRDF textures from a single neutral-expression face. Our method employs an attention-based diffusion model to learn the semantic transition across expressions. To ensure correspondence between geometry and texture, we introduce a unified representation that explicitly models geometric-textural interaction, which is encoded into a shared latent space by models pre-trained on a vast dataset for strong generalization. To achieve semantically coherent and physically consistent generation, we propose to guide the denoising direction with specially designed textual prompts. We further construct two novel facial expression datasets, J-Reflectance, for ultra-high-quality assets, and FFHQ-BRDFExp for diverse identities, both of which are publicly released to advance the community. Extensive experiments demonstrate our method's superior performance in photo-realistic facial expression synthesis. Project page: https://cyh-sj.github.io/expdiff/.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP  (15209210) , 1-13
ExpDiff: Generating High-Fidelity 3D Facial Expression Meshes and BRDF Textures Via Diffusion Model
3D face generation is a critical task for immersive multimedia applications, where a key challenge is the joint synthesis of expressive geometry and BRDF textures. Existing methods often struggle with geometric-textural coherence and corresponding reflectance modeling. To overcome these limitations, we present ExpDiff, a framework that generates expression meshes and corresponding BRDF textures from a single neutral-expression face. Our method employs an attention-based diffusion model to learn the semantic transition across expressions. To ensure correspondence between geometry and texture, we introduce a unified representation that explicitly models geometric-textural interaction, which is encoded into a shared latent space by models pre-trained on a vast dataset for strong generalization. To achieve semantically coherent and physically consistent generation, we propose to guide the denoising direction with specially designed textual prompts. We further construct two novel facial expression datasets, J-Reflectance, for ultra-high-quality assets, and FFHQ-BRDFExp for diverse identities, both of which are publicly released to advance the community. Extensive experiments demonstrate our method's superior performance in photo-realistic facial expression synthesis. Project page: https://cyh-sj.github.io/expdiff/.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (3) , 2312-2328
Topo4D++: Realistic Physically Based 4D Head Capture With Topology-Preserving Gaussian Splatting and Expression Priors
4D head capture aims to generate dynamic facial meshes in the same topology with corresponding UV maps, which requires temporal correspondence between 3D head models. Existing pipelines either involve manual processing of artists or employ constraints such as landmark tracking and optical flow, failing to achieve a trade-off between accuracy and efficiency. To enhance this process, we propose Topo4D++, a novel framework for automatic geometry and texture reconstruction that optimizes densely aligned 4D heads and 8 K BRDF maps directly from calibrated multi-view videos. Our key insight is to represent facial models as a set of dynamic 3D Gaussians with fixed topology, where the Gaussian centers are bound to the mesh vertices. This enables tracking all vertices rather than sparse vertices on the face accurately by leveraging the inverse rendering capabilities of 3D Gaussian Splatting (3DGS), while also enabling ultra-high-resolution texture generation. To maintain face structure during dynamic 3DGS optimization, we propose to optimize geometry and texture alternatively under physical and topological constraints frame-by-frame and employ blendshape-based expression priors to address extreme expressions. Then, we propose to extract dynamic facial meshes in a regular wiring arrangement and high-fidelity textures with pore-level details from the learned Gaussians. Finally, we train a diffusion-based model to generate BRDF texture maps to achieve physically based rendering. Given the absence of a universal benchmark, we construct JHead, a novel benchmark for the comprehensive evaluation of 4D head capture methods. Extensive experiments on different datasets demonstrate that our method is generalized to different capture systems, identities, and expressions, outperforming current state-of-the-art head reconstruction methods in both mesh and texture qualitatively and quantitatively.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (3) , 2312-2328
Topo4D++: Realistic Physically Based 4D Head Capture With Topology-Preserving Gaussian Splatting and Expression Priors
4D head capture aims to generate dynamic facial meshes in the same topology with corresponding UV maps, which requires temporal correspondence between 3D head models. Existing pipelines either involve manual processing of artists or employ constraints such as landmark tracking and optical flow, failing to achieve a trade-off between accuracy and efficiency. To enhance this process, we propose Topo4D++, a novel framework for automatic geometry and texture reconstruction that optimizes densely aligned 4D heads and 8 K BRDF maps directly from calibrated multi-view videos. Our key insight is to represent facial models as a set of dynamic 3D Gaussians with fixed topology, where the Gaussian centers are bound to the mesh vertices. This enables tracking all vertices rather than sparse vertices on the face accurately by leveraging the inverse rendering capabilities of 3D Gaussian Splatting (3DGS), while also enabling ultra-high-resolution texture generation. To maintain face structure during dynamic 3DGS optimization, we propose to optimize geometry and texture alternatively under physical and topological constraints frame-by-frame and employ blendshape-based expression priors to address extreme expressions. Then, we propose to extract dynamic facial meshes in a regular wiring arrangement and high-fidelity textures with pore-level details from the learned Gaussians. Finally, we train a diffusion-based model to generate BRDF texture maps to achieve physically based rendering. Given the absence of a universal benchmark, we construct JHead, a novel benchmark for the comprehensive evaluation of 4D head capture methods. Extensive experiments on different datasets demonstrate that our method is generalized to different capture systems, identities, and expressions, outperforming current state-of-the-art head reconstruction methods in both mesh and texture qualitatively and quantitatively.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27  (15209210) , 7961-7973
Revealing Directions for Text-Guided 3D Face Editing
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation. Our project page: https://windlikestone.github.io/Face_clan_website/.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27  (15209210) , 7961-7973
Revealing Directions for Text-Guided 3D Face Editing
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation. Our project page: https://windlikestone.github.io/Face_clan_website/.
- Open Access
Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture
Significant progress has been made for speech-driven 3D face animation, but most works focus on learning the motion of mesh/geometry, ignoring the impact of dynamic texture. In this work, we reveal that dynamic texture plays a key role in rendering high-fidelity talking avatars, and introduce a high-resolution 4D dataset \textbf{TexTalk4D}, consisting of 100 minutes of audio-synced scan-level meshes with detailed 8K dynamic textures from 100 subjects. Based on the dataset, we explore the inherent correlation between motion and texture, and propose a diffusion-based framework \textbf{TexTalker} to simultaneously generate facial motions and dynamic textures from speech. Furthermore, we propose a novel pivot-based style injection strategy to capture the complicity of different texture and motion styles, which allows disentangled control. TexTalker, as the first method to generate audio-synced facial motion with dynamic texture, not only outperforms the prior arts in synthesising facial motions, but also produces realistic textures that are consistent with the underlying facial movements. Project page: https://xuanchenli.github.io/TexTalk/.
Open AccessTowards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture
Significant progress has been made for speech-driven 3D face animation, but most works focus on learning the motion of mesh/geometry, ignoring the impact of dynamic texture. In this work, we reveal that dynamic texture plays a key role in rendering high-fidelity talking avatars, and introduce a high-resolution 4D dataset \textbf{TexTalk4D}, consisting of 100 minutes of audio-synced scan-level meshes with detailed 8K dynamic textures from 100 subjects. Based on the dataset, we explore the inherent correlation between motion and texture, and propose a diffusion-based framework \textbf{TexTalker} to simultaneously generate facial motions and dynamic textures from speech. Furthermore, we propose a novel pivot-based style injection strategy to capture the complicity of different texture and motion styles, which allows disentangled control. TexTalker, as the first method to generate audio-synced facial motion with dynamic texture, not only outperforms the prior arts in synthesising facial motions, but also produces realistic textures that are consistent with the underlying facial movements. Project page: https://xuanchenli.github.io/TexTalk/.
- 31 October 2024
- Published by Springer Nature
- p. 128-145
Topo4D: Topology-Preserving Gaussian Splatting for High-fidelity 4D Head Capture
- 31 October 2024
- Published by Springer Nature
- p. 128-145
Topo4D: Topology-Preserving Gaussian Splatting for High-fidelity 4D Head Capture
- Open Access
Revealing Directions for Text-guided 3D Face Editing
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation.
Open AccessRevealing Directions for Text-guided 3D Face Editing
3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation.
- Open Access
- 8 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20  (6) , 1-20
Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full-head generation methods require a large number of three-dimensional (3D) scans or multi-view images to train the model, resulting in expensive data acquisition costs. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces within complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present a dual-discriminator to guide the frontal and back head generation. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.
- 8 March 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20  (6) , 1-20
Open AccessHead3D: Complete 3D Head Generation via Tri-plane Feature Distillation
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full-head generation methods require a large number of three-dimensional (3D) scans or multi-view images to train the model, resulting in expensive data acquisition costs. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces within complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present a dual-discriminator to guide the frontal and back head generation. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.
- Open Access
GANHead: Towards Generative Animatable Neural Head Avatars
To bring digital avatars into people's lives, it is highly demanded to efficiently generate complete, realistic, and animatable head avatars. This task is challenging, and it is difficult for existing methods to satisfy all the requirements at once. To achieve these goals, we propose GANHead (Generative Animatable Neural Head Avatar), a novel generative head model that takes advantages of both the fine-grained control over the explicit expression parameters and the realistic rendering results of implicit representations. Specifically, GANHead represents coarse geometry, fine-gained details and texture via three networks in canonical space to obtain the ability to generate complete and realistic head avatars. To achieve flexible animation, we define the deformation filed by standard linear blend skinning (LBS), with the learned continuous pose and expression bases and LBS weights. This allows the avatars to be directly animated by FLAME parameters and generalize well to unseen poses and expressions. Compared to state-of-the-art (SOTA) methods, GANHead achieves superior performance on head avatar generation and raw scan fitting.
Open AccessGANHead: Towards Generative Animatable Neural Head Avatars
To bring digital avatars into people's lives, it is highly demanded to efficiently generate complete, realistic, and animatable head avatars. This task is challenging, and it is difficult for existing methods to satisfy all the requirements at once. To achieve these goals, we propose GANHead (Generative Animatable Neural Head Avatar), a novel generative head model that takes advantages of both the fine-grained control over the explicit expression parameters and the realistic rendering results of implicit representations. Specifically, GANHead represents coarse geometry, fine-gained details and texture via three networks in canonical space to obtain the ability to generate complete and realistic head avatars. To achieve flexible animation, we define the deformation filed by standard linear blend skinning (LBS), with the learned continuous pose and expression bases and LBS weights. This allows the avatars to be directly animated by FLAME parameters and generalize well to unseen poses and expressions. Compared to state-of-the-art (SOTA) methods, GANHead achieves superior performance on head avatar generation and raw scan fitting.
- Open Access
Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full head generation methods require a large number of 3D scans or multi-view images to train the model, resulting in expensive data acquisition cost. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces into complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present dual-discriminators to guide the frontal and back head generation, respectively. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.
Open AccessHead3D: Complete 3D Head Generation via Tri-plane Feature Distillation
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full head generation methods require a large number of 3D scans or multi-view images to train the model, resulting in expensive data acquisition cost. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver the 3D frontal faces into complete heads without compromising head integrity. To mitigate the domain gap between the face and head models, we present dual-discriminators to guide the frontal and back head generation, respectively. Our model achieves cost-efficient and diverse complete head generation with photo-realistic renderings and high-quality geometry representations. Extensive experiments demonstrate the effectiveness of our proposed Head3D, both qualitatively and quantitatively.