Ting-Chun Wang

Principal Research Scientist

NVIDIA

Santa Clara, CA

Email:

tingchunw at nvidia dot com

 

GitHub | Google Scholar

 

I'm a principal research scientist at the Deep Imagination Research (DIR) group at NVIDIA, working on computer vision, machine learning, and computer graphics.
I received my PhD from University of California, Berkeley, advised by Professor Ravi Ramamoorthi and Alexei A. Efros.
My recent research focus is on using generative models to synthesize realistic images and videos, with applications to rendering, visual manipulations and beyond. See our NVIDIA Picasso (Edify) page.


News

Selected Publications

dreampose

DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion

 

Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman

 

International Conference on Computer Vision (ICCV), 2023

 

project | paper | code | bibtex

@inproceedings{karras2023dreampose,
    title={{Dreampose: Fashion image-to-video synthesis via stable diffusion}},
    author={Karras, Johanna and Holynski, Aleksander and Wang, Ting-Chun and Kemelmacher-Shlizerman, Ira},
    booktitle={ICCV},
    year={2023}
}
      
space

SPACE: Speech-driven Portrait Animation with Controllable Expression

 

Siddharth Gururani, Arun Mallya, Ting-Chun Wang, Rafael Valle, Ming-Yu Liu

 

International Conference on Computer Vision (ICCV), 2023

 

project | paper | bibtex

@inproceedings{gururani2022SPACE,
    title={{SPACE: Speech-driven Portrait Animation with Controllable Expression}},
    author={Siddharth Gururani and Arun Mallya and Ting-Chun Wang and Rafael Valle and Ming-Yu Liu},
    booktitle={ICCV},
    year={2023}
}
      
implicit_warp

Implicit Warping for Animation with Image Sets

 

Arun Mallya, Ting-Chun Wang, Ming-Yu Liu

 

Conference on Neural Information Processing Systems (NeurIPS), 2022

 

project | paper | bibtex

@inproceedings{mallya2022implicit,
    title={{Implicit Warping for Animation with Image Sets}},
    author={Arun Mallya and Ting-Chun Wang and Ming-Yu Liu},
    booktitle={NeurIPS},
    year={2022}
}
      
video_gan

Generating Long Videos of Dynamic Scenes

 

Tim Brooks, Janne Hellsten, Miika Aittala, Ting-Chun Wang, Timo Aila, Jaakko Lehtinen, Ming-Yu Liu, Alexei A. Efros, Tero Karras

 

Conference on Neural Information Processing Systems (NeurIPS), 2022

 

project | paper | code | bibtex

@inproceedings{brooks2022generating,
  title={Generating Long Videos of Dynamic Scenes},
  author={Brooks, Tim and Hellsten, Janne and Aittala, Miika and Wang, Ting-Chun and Aila, Timo and Lehtinen, Jaakko and Liu, Ming-Yu and Efros, Alexei A and Karras, Tero},
  booktitle=NeurIPS,
  year={2022}
}
      
lumos

Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation

 

Yu-Ying Yeh, Koki Nagano, Sameh Khamis, Jan Kautz, Ming-Yu Liu, Ting-Chun Wang

 

ACM Transactions on Graphics (SIGGRAPH Asia), 2022

 

project | paper | YouTube | demo | bibtex

@article{yeh2022learning,
    title={Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation},
    author={Yu-Ying Yeh and Koki Nagano and Sameh Khamis and Jan Kautz and Ming-Yu Liu and Ting-Chun Wang},
    journal={ACM Transactions on Graphics (TOG)},
    year={2022}
}
      
poegan

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

 

Xun Huang, Arun Mallya, Ting-Chun Wang, Ming-Yu Liu

 

European Conference on Computer Vision (ECCV), 2022

 

project | paper | YouTube | demo | bibtex

@inproceedings{huang2022poegan,
    title={Multimodal Conditional Image Synthesis with Product-of-Experts {GANs}},
    author={Xun Huang and Arun Mallya and Ting-Chun Wang and Ming-Yu Liu},
    booktitle={ECCV},
    year={2022}
}
      
pconv_tpami

Partial Convolution for Padding, Inpainting, and Image Synthesis

 

Guilin Liu, Aysegul Dundar, Kevin J. Shih, Ting-Chun Wang, Fitsum A. Reda, Karan Sapra, Zhiding Yu, Xiaodong Yang, Andrew Tao, Bryan Catanzaro

 

Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

 

paper | bibtex

@article{liu2022partial,
  title={Partial Convolution for Padding, Inpainting, and Image Synthesis}, 
  author={Liu, Guilin and Dundar, Aysegul and Shih, Kevin J. and Wang, Ting-Chun and Reda, Fitsum A. and Sapra, Karan and Yu, Zhiding and Yang, Xiaodong and Tao, Andrew and Catanzaro, Bryan},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  year={2022},
}
      
facevid2vid

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

 

Ting-Chun Wang, Arun Mallya, Ming-Yu Liu

 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (oral presentation)

 

project | paper | YouTube | Talk | Slides | Poster | bibtex

@inproceedings{wang2021facevid2vid,
   author    = {Ting-Chun Wang and Arun Mallya and Ming-Yu Liu},
   title     = {One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing},
   booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
   year      = {2021},
}
      
transposer_tog

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

 

Guilin Liu, Rohan Taori, Ting-Chun Wang, Zhiding Yu, Shiqiu Liu, Fitsum A. Reda, Karan Sapra, Andrew Tao, Bryan Catanzaro

 

ACM Transactions on Graphics, 2021 (provisionally accepted)

 

paper | YouTube | bibtex

@article{liu2021transposer,
   author  = {Guilin Liu and Rohan Taori and Ting-Chun Wang and Zhiding Yu and Shiqiu Liu 
              and Fitsum Reda and Karan Sapra and Andrew Tao and Bryan Catanzaro},
   title   = {Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter},
   journal = {ACM Transactions on Graphics},
   year      = {2021}
}
      
gan_survey

Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications

 

Ming-Yu Liu, Xun Huang, Jiahui Yu, Ting-Chun Wang, Arun Mallya

 

Proceedings of The IEEE, 2021

 

paper | bibtex

          
@article{liu2021generative,
   title={Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications},
   author={Ming-Yu Liu and Xun Huang and Jiahui Yu and Ting-Chun Wang and Arun Mallya},
   journal={Proceedings of The IEEE},
   year={2021}
}
  
wcvid2vid_eccv

World-Consistent Video-to-Video Synthesis

 

Arun Mallya*, Ting-Chun Wang*, Karan Sapra, Ming-Yu Liu (*equal contribution)

 

European Conference on Computer Vision (ECCV), 2020

 

project | paper | YouTube | bibtex

          
@inproceedings{mallya2020world,
   author    = {Arun Mallya and Ting-Chun Wang and Karan Sapra and Ming-Yu Liu},
   title     = {World-Consistent Video-to-Video Synthesis},  
   booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},   
   year      = {2020},
}
      
ds_tpami

Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation

 

Aysegul Dundar, Ming-Yu Liu, Zhiding Yu, Ting-Chun Wang, John Zedlewski, Jan Kautz

 

Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020

 

paper | bibtex

@article{dundar2020domain,
  title={Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation},
  author={Aysegul Dundar and Ming-Yu Liu and Zhiding Yu and Ting-Chun Wang and John Zedlewski and and Jan Kautz},
  booktitle={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year={2020}
}
      
avid2vid_nips

Few-shot Video-to-Video Synthesis

 

Ting-Chun Wang, Ming-Yu Liu, Andrew Tao, Guilin Liu, Jan Kautz, Bryan Catanzaro

 

Conference on Neural Information Processing Systems (NeurIPS), 2019

 

project | paper | github | YouTube | bibtex

@inproceedings{wang2019fewshotvid2vid,
  title={Few-shot Video-to-Video Synthesis},
  author={Ting-Chun Wang and Ming-Yu Liu and Andrew Tao and Guilin Liu and Jan Kautz and Bryan Catanzaro},
  booktitle={Conference on Neural Information Processing Systems (NeurIPS)},
  year={2019}
}
      
d2m_nips

Dancing to Music

 

Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang, Yu-Ding Lu, Ming-Hsuan Yang, Jan Kautz

 

Conference on Neural Information Processing Systems (NeurIPS), 2019

 

paper | github | YouTube | bibtex

@inproceedings{lee2019dancing2music,
  title={Dancing to Music},
  author={Hsin-Ying Lee and Xiaodong Yang and Ming-Yu Liu and Ting-Chun Wang and Yu-Ding Lu and Ming-Hsuan Yang and Jan Kautz},
  booktitle={Conference on Neural Information Processing Systems (NeurIPS)},
  year={2019}
}
      
spade_cvpr

Semantic Image Synthesis with Spatially-Adaptive Normalization

 

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (best paper finalist)

 

project | paper | github | YouTube | bibtex

@inproceedings{park2019SPADE,
  title={Semantic Image Synthesis with Spatially-Adaptive Normalization},
  author={Park, Taesung and Liu, Ming-Yu and Wang, Ting-Chun and Zhu, Jun-Yan},
  booktitle={Proceedings of the IEEE Conference on 
             Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}
      
vid2vid_nips

Video-to-Video Synthesis

 

Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Guilin Liu, Andrew Tao, Jan Kautz, Bryan Catanzaro

 

Conference on Neural Information Processing Systems (NeurIPS), 2018

 

project | paper | arXiv | github | YouTube | bibtex

@inproceedings{wang2018vid2vid,
   author    = {Ting-Chun Wang and Ming-Yu Liu and Jun-Yan Zhu and Guilin Liu
                and Andrew Tao and Jan Kautz and Bryan Catanzaro},
   title     = {Video-to-Video Synthesis},
   booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},   
   year      = {2018},
}
      
partconv_arxiv

Partial Convolution based Padding

 

Guilin Liu, Kevin J. Shih, Ting-Chun Wang, Fitsum A. Reda, Karan Sapra, Zhiding Yu, Andrew Tao, Bryan Catanzaro

 

arXiv preprint arXiv:1811.11718

 

arXiv | bibtex

          
@article{liu2018partial,
   author    = {Liu, Guilin and Shih, Kevin J and Wang, Ting-Chun and Reda, Fitsum A 
                and Sapra, Karan and Yu, Zhiding and Tao, Andrew and Catanzaro, Bryan},
   title     = {Partial convolution based padding},
   journal   = {arXiv preprint arXiv:1811.11718},
   year      = {2018},
}
      
ds_arxiv

Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation

 

Aysegul Dundar, Ming-Yu Liu, Ting-Chun Wang, John Zedlewski, Jan Kautz

 

arXiv preprint arXiv:1807.09384

 

arXiv | bibtex

@article{dundar2018domain,
  title={Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation},
  author={Dundar, Aysegul and Liu, Ming-Yu and Wang, Ting-Chun and Zedlewski, John and Kautz, Jan},
  journal={arXiv preprint arXiv:1807.09384},
  year={2018}
}
      
parconv_eccv

Image Inpainting for Irregular Holes Using Partial Convolutions

 

Guilin Liu, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, Bryan Catanzaro

 

European Conference on Computer Vision (ECCV), 2018

 

project | arXiv | YouTube | bibtex

          
@inproceedings{liu2018image,
   author    = {Liu, Guilin and Reda, Fitsum A and Shih, Kevin J 
                and Wang, Ting-Chun and Tao, Andrew and Catanzaro, Bryan},
   title     = {Image inpainting for irregular holes using partial convolutions},
   booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},   
   year      = {2018},
}
      
pix2pixHD_cvpr

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

 

Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, Bryan Catanzaro

 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (oral presentation)

 

project | paper | arXiv | github | YouTube | slides | bibtex

@inproceedings{wang2018pix2pixHD,
   author    = {Ting-Chun Wang and Ming-Yu Liu and Jun-Yan Zhu 
                and Andrew Tao and Jan Kautz and Bryan Catanzaro},
   title     = {High-Resolution Image Synthesis and Semantic Manipulation 
                with Conditional GANs},
   booktitle = {Proceedings of the IEEE Conference on 
                Computer Vision and Pattern Recognition (CVPR)},   
   year      = {2018},
}
      
thesis

Beyond Photo-Consistency: Shape, Reflectance, and Material Estimation Using
Light-Field Cameras

 

Ting-Chun Wang

 

PhD Thesis, 2017

 


Professional Activities

 

Tutorial/Workshop Co-organizer

Conference Area Chair: ECCV, ICLR, WACV

 

Conference Reviewer: CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, Eurographics, NeurIPS, ICLR, ICRA

 

Journal Reviewer: TPAMI, IJCV, TOG, TIP, TMM, TVCG, TCSVT, CVIU



Awards


Software

Imaginaire: a common codebase for training generative models.

Few-shot vid2vid: Few-shot video-to-video translation.

SPADE: Semantic image synthesis on diverse datasets including Flickr and coco.

vid2vid: High-resolution video-to-video translation.

pix2pixHD: High-resolution image-to-image translation.



Talks

Face-vid2vid: One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

CVPR (2021)

 

Few-Shot Video-to-Video Synthesis

ICCV Workshop on Advances in Image Manipulation (2019)

 

Mixed-Precision Training for pix2pixHD

ICCV Tutorial on Accelerating Computer Vision with Mixed Precision (2019)

 

Image-to-Image Translation

ICIP Tutorial on Image-to-Image Translation (2019)

 

Video-to-Video Synthesis

CVPR Workshop on Deep Learning for Content Creation (2019)

 

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (pix2pixHD)

CVPR (2018)

 

Beyond Photo-Consistency: Shape, Reflectance, and Material Estimation Using Light-Field Cameras

Dissertation talk (2017)

 


web page statistics from GoStats