Wanhu Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wanhu Sun has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoguang Han
The Chinese University of Hong Kong, Shenzhen, Shenzhen, China
3 shared publications - Jiahao Chang
SSE, CUHKSZ, Shenzhen, China
2 shared publications - Bowen Zhao
Department of Physics Boston University 590 Commonwealth Avenue 02215 Boston Massachusetts USA
1 shared publication - Chenghong Li
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen
1 shared publication Chongjie Ye
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China
1 shared publication- Chongjie Ye
FNii-Shenzhen, Shenzhen, China and SSE, CUHKSZ, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
SAM3D-Part: Interactive Part Selection and Generation from 3D Objects
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessSAM3D-Part: Interactive Part Selection and Generation from 3D Objects
- 3 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (10) , 7820-7833
StruGauAvatar: Learning Structured 3D Gaussians for Animatable Avatars From Monocular Videos
In recent years, significant progress has been witnessed in the field of neural 3D avatar reconstruction. Among all related tasks, building an animatable avatar from monocular videos is one of the most challenging ones, yet it also has a wide range of applications. The “animatable” means that we need to transfer any arbitrary and unseen poses onto the avatar and generate new 3D videos. Thanks to the rise of the powerful representation of NeRF, generating a high-fidelity animatable avatar from videos has become easier and more accessible. Despite their impressive visual results, the substantial training and rendering overhead dramatically hamper their applications. 3D Gaussian Splatting, as a timely new representation, has demonstrated its high-quality and high-efficiency rendering. This has led to many concurrent works to introduce 3D-GS to animatable avatar building. Although they demonstrate very high-fidelity renderings for poses similar to the training video frames, poor results are produced when the poses are far from training. We argue that this is primarily because the Gaussian points lack structures. Thus, we suggest involving DMTet to represent the coarse geometry of the avatar. In our representation, the majority of Gaussian points are bound to the mesh vertices, while some free Gaussian is allowed to expand to better fit the given video. Furthermore, we develop a dual-space optimization framework to jointly optimize the DMTet, Gaussian points, and skinning weights under two spaces. In this sense, Gaussian points are transformed in a constrained way, which dramatically improves the generalization ability for unseen poses. This is well demonstrated via extensive experiments.
- 3 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (10) , 7820-7833
StruGauAvatar: Learning Structured 3D Gaussians for Animatable Avatars From Monocular Videos
In recent years, significant progress has been witnessed in the field of neural 3D avatar reconstruction. Among all related tasks, building an animatable avatar from monocular videos is one of the most challenging ones, yet it also has a wide range of applications. The “animatable” means that we need to transfer any arbitrary and unseen poses onto the avatar and generate new 3D videos. Thanks to the rise of the powerful representation of NeRF, generating a high-fidelity animatable avatar from videos has become easier and more accessible. Despite their impressive visual results, the substantial training and rendering overhead dramatically hamper their applications. 3D Gaussian Splatting, as a timely new representation, has demonstrated its high-quality and high-efficiency rendering. This has led to many concurrent works to introduce 3D-GS to animatable avatar building. Although they demonstrate very high-fidelity renderings for poses similar to the training video frames, poor results are produced when the poses are far from training. We argue that this is primarily because the Gaussian points lack structures. Thus, we suggest involving DMTet to represent the coarse geometry of the avatar. In our representation, the majority of Gaussian points are bound to the mesh vertices, while some free Gaussian is allowed to expand to better fit the given video. Furthermore, we develop a dual-space optimization framework to jointly optimize the DMTet, Gaussian points, and skinning weights under two spaces. In this sense, Gaussian points are transformed in a constrained way, which dramatically improves the generalization ability for unseen poses. This is well demonstrated via extensive experiments.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-12
GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details
Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD) , spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under-constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches while being robust against a large variation of pose, illumination, occlusion, and deformation. Code and dataset are available at garverselod.github.io.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-12
Open AccessGarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details
Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD) , spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under-constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches while being robust against a large variation of pose, illumination, occlusion, and deformation. Code and dataset are available at garverselod.github.io.