2D/3D Face Vision & Graphics

3D face shape & texture reconstruction, face alignment, face recognition

Understanding and generating human faces is a fundamental and important research topic within computer vision. PI has extensive experience in research and development related to human face analysis, spanning areas such as face detection, recognition, image synthesis, 3D face reconstruction, novel-view rendering of faces, and more. Many of these algorithms have been shipped to Microsoft Azure AI services and other products (Huang et al., 2021), (Huang et al., 2023), (Kim et al., 2021).

Constructing 3D Face Morphable Model (3DMM) using a raw 3D scanned data.

In the context of 3D face reconstruction, a common approach involves utilizing a 3D face morphable model, which offers a robust prior understanding of human facial shape and texture.

Face Texture Completion.
Face Alignment.

References

2023

  1. AAAI
    FreeEnricher: Enriching Face Landmarks without Additional Cost
    Yangyu Huang, Xi Chen, Jongyoo Kim, and 4 more authors
    In AAAI Conference on Artificial Intelligence, 2023

2021

  1. ICCV
    ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
    Yangyu Huang, Hao Yang, Chong Li, and 2 more authors
    In IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2021
  2. ICCV
    Learning High-Fidelity Face Texture Completion without Complete Face Texture
    Jongyoo Kim, Jiaolong Yang, and Xin Tong
    In IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2021