no code implementations • 24 Jun 2024 • Yufei Liu, Junshu Tang, Chu Zheng, Shijie Zhang, Jinkun Hao, Junwei Zhu, Dongjin Huang
We propose a novel representation Disentangled Clothe Gaussian Splatting (DCGS) to enable separate optimization.
no code implementations • 24 Jun 2024 • Jinkun Hao, Junshu Tang, Jiangning Zhang, Ran Yi, Yijia Hong, Moran Li, Weijian Cao, Yating Wang, Chengjie Wang, Lizhuang Ma
We then use the canny map, ID features of the portrait image, and a pre-trained text-to-normal/depth diffusion model to generate ID-aware geometry supervision, and 3D-GAN inversion is employed to generate ID-aware geometry initialization.
no code implementations • 4 Jun 2024 • Yuzhou Ji, He Zhu, Junshu Tang, Wuyi Liu, Zhizhong Zhang, Xin Tan, Yuan Xie
The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications.
no code implementations • 24 May 2024 • Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Lizhuang Ma
Text-to-motion synthesis is a crucial task in computer vision.
Ranked #5 on
Motion Synthesis
on InterHuman
no code implementations • CVPR 2024 • Junshu Tang, Yanhong Zeng, Ke Fan, Xuheng Wang, Bo Dai, Kai Chen, Lizhuang Ma
Creating and animating 3D biped cartoon characters is crucial and valuable in various applications.
no code implementations • 19 Mar 2024 • Yufei Liu, Junwei Zhu, Junshu Tang, Shijie Zhang, Jiangning Zhang, Weijian Cao, Chengjie Wang, Yunsheng Wu, Dongjin Huang
Texturing 3D humans with semantic UV maps remains a challenge due to the difficulty of acquiring reasonably unfolded UV.
2 code implementations • ICCV 2023 • Junshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, Dong Chen
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image.
1 code implementation • 12 Sep 2022 • Junshu Tang, Bo Zhang, Binxin Yang, Ting Zhang, Dong Chen, Lizhuang Ma, Fang Wen
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs.
no code implementations • 5 Sep 2022 • Junshu Tang, Jiachen Xu, Jingyu Gong, Haichuan Song, Yuan Xie, Lizhuang Ma
Moreover, for effective training, we consider difficulty-based sampling strategy to encourage the network to pay more attention to some partial point clouds with fewer geometric information.
1 code implementation • CVPR 2022 • Junshu Tang, Zhijun Gong, Ran Yi, Yuan Xie, Lizhuang Ma
An asymmetric keypoint locator, including an unsupervised multi-scale keypoint detector and a complete keypoint generator, is proposed for localizing aligned keypoints from complete and partial point clouds.
1 code implementation • 21 Apr 2020 • Junshu Tang, Zhiwen Shao, Lizhuang Ma
Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details.
no code implementations • 6 Sep 2019 • Zhiwen Shao, Hengliang Zhu, Junshu Tang, Xuequan Lu, Lizhuang Ma
Instead of using an intermediate estimated guidance, we propose to explicitly transfer facial expression by directly mapping two unpaired input images to two synthesized images with swapped expressions.