Yajing Chen
Research Subjects
Yajing Chen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Xin Wang
LIGHTSPEED, Shenzhen, China
2 shared publications - Changyu Hu
Tsinghua University, Beijing, China
1 shared publication - Cheng Zeng
Tsinghua University, Shenzhen, China
1 shared publication Fanzi Wu
Chinese University of Hong Kong
1 shared publication- Haidi Fan
LIGHTSPEED, Shenzhen, China
1 shared publication - Jingya Wang
ShanghaiTech University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
TailorRig: Controllable and Structured Auxiliary Skeleton Generation for Garment-Aware Rigging
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessTailorRig: Controllable and Structured Auxiliary Skeleton Generation for Garment-Aware Rigging
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3863-3872
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3863-3872
Open AccessSuper Star: Towards Streaming Real-time Interactive Agents for Digital Humans
- 27 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 8696-8705
Self-Supervised Learning of Detailed 3D Face Reconstruction
In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image1. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-toimage translation network to predict a displacement map in UVspace. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of the proposed method over previous work.
- 27 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 8696-8705
Self-Supervised Learning of Detailed 3D Face Reconstruction
In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image1. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-toimage translation network to predict a displacement map in UVspace. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of the proposed method over previous work.