1. 

   Face Relighting with Geometrically Consistent Shadows

   Andrew Hou, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu

   Most face relighting methods are able to handle diffuse shadows, but struggle to handle hard shadows, such as those cast by the nose. Methods that propose techniques for handling hard shadows often do not produce geometrically consistent shadows since they do not directly leverage the estimated face geometry while synthesizing ...

   Continue reading

   Keywords: Face Relighting, Low-level Vision

2. 

   Towards High Fidelity Face Relighting with Realistic Shadows

   Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu

   Existing face relighting methods often struggle with two problems: maintaining the local facial details of the subject and accurately removing and synthesizing shadows in the relit image, especially hard shadows. We propose a novel deep face relighting method that addresses both problems. Our method learns to predict the ratio (quotient ...

   Continue reading

   Keywords: Face Relighting, Low-level Vision

3. 

   Unconstrained 3D Face Reconstruction

   Joseph Roth, Yiying Tong, Xiaoming Liu

   We present an algorithm for "unconstrained" 3D face reconstruction from a 2D photo collection of face images of a subject captured under a diverse variation of poses, expressions, and illuminations, without meta data about the cameras, timing, or light conditions. The output of our algorithm is a true 3D face ...

   Continue reading

   Keywords: Face reconstruction, 3D shape reconstruction

2023

• INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields
  Andrew Hou, Feng Liu, Zhiyuan Ren, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
  arxiv, Dec. 2023
  Bibtex | arXiv
@inproceedings{ infamous-nerf-improving-face-modeling-using-semantically-aligned-hypernetworks-with-neural-radiance-fields,
  author = { Andrew Hou and Feng Liu and Zhiyuan Ren and Michel Sarkis and Ning Bi and Yiying Tong and Xiaoming Liu },
  title = { INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields },
  booktitle = { arxiv },
  address = { },
  month = { December },
  year = { 2023 },
}

2022

• Face Relighting with Geometrically Consistent Shadows
  Andrew Hou, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, Jun. 2022
  Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code | Video
@inproceedings{ face-relighting-with-geometrically-consistent-shadows,
  author = { Andrew Hou and Michel Sarkis and Ning Bi and Yiying Tong and Xiaoming Liu },
  title = { Face Relighting with Geometrically Consistent Shadows },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { New Orleans, LA },
  month = { June },
  year = { 2022 },
}

2021

• Towards High Fidelity Face Relighting with Realistic Shadows
  Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2021), Nashville, TN, Jun. 2021
  Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code | Video
@inproceedings{ towards-high-fidelity-face-relighting-with-realistic-shadows,
  author = { Andrew Hou and Ze Zhang and Michel Sarkis and Ning Bi and Yiying Tong and Xiaoming Liu },
  title = { Towards High Fidelity Face Relighting with Realistic Shadows },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Nashville, TN },
  month = { June },
  year = { 2021 },
}

2016

• Adaptive 3D Face Reconstruction from Unconstrained Photo Collections
  Joseph Roth, Yiying Tong, Xiaoming Liu
  IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 11, pp.2127-2141, , Dec. 2016
  Bibtex | PDF | Project Webpage
@article{ adaptive-3d-face-reconstruction-from-unconstrained-photo-collections,
  author = { Joseph Roth and Yiying Tong and Xiaoming Liu },
  title = { Adaptive 3D Face Reconstruction from Unconstrained Photo Collections },
  journal = { IEEE Transactions on Pattern Analysis and Machine Intelligence },
  volume = { 39 },
  number = { 11 },
  month = { December },
  year = { 2016 },
  pages = { 2127--2141 },
}
• Adaptive 3D Face Reconstruction from Unconstrained Photo Collections
  Joseph Roth, Yiying Tong, Xiaoming Liu
  Proc. IEEE Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, Jun. 2016
  Bibtex | PDF | Poster | Project Webpage
@inproceedings{ adaptive-3d-face-reconstruction-from-unconstrained-photo-collections,
  author = { Joseph Roth and Yiying Tong and Xiaoming Liu },
  title = { Adaptive 3D Face Reconstruction from Unconstrained Photo Collections },
  booktitle = { Proc. IEEE Computer Vision and Pattern Recognition },
  address = { Las Vegas, NV },
  month = { June },
  year = { 2016 },
}

2015

• Unconstrained 3D Face Reconstruction
  Joseph Roth, Yiying Tong, Xiaoming Liu
  Proc. IEEE Computer Vision and Pattern Recognition (CVPR 2015), Bostan, MA, Jun. 2015 (Acceptance rate 28%)
  Bibtex | PDF | Poster | Project Webpage
@inproceedings{ unconstrained-3d-face-reconstruction,
  author = { Joseph Roth and Yiying Tong and Xiaoming Liu },
  title = { Unconstrained 3D Face Reconstruction },
  booktitle = { Proc. IEEE Computer Vision and Pattern Recognition },
  address = { Bostan, MA },
  month = { June },
  year = { 2015 },
}