Biography

---

Kelvin is a Senior Research Scientist at Google DeepMind, where he works on low-level vision and multimodal generation. He earned his B.Sc. and B.Eng. degrees from The Chinese University of Hong Kong, and his M.Phil. degree in Mathematics from the same university. He then went on to receive his Ph.D. in Computer Science from Nanyang Technological University in Singapore, where he was supervised by Prof. Chen Change Loy at MMLab@NTU. He was awarded the NTU SCSE Outstanding PhD Thesis Award in 2023 for his research on low-level vision. He is a recipient of the Google PhD Fellowship in 2021.

Publications

---

Technical Report

• 

  Imagen 3
  Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Kelvin C.K. Chan, Yichang Chen, Sander Dieleman, Yuqing Du et al.
  arXiv preprint arXiv:2408.07009
  

  • [PDF]
  • [Web]
  • [BibTeX]

  @article{baldridge2024imagen,
  author = {Baldridge, Jason and Bauer, Jakob and Bhutani, Mukul and Brichtova, Nicole and Bunner, Andrew and Chan, Kelvin C.K. and Chen, Yichang and Dieleman, Sander and Du, Yuqing et al.},
  title = {Imagen 3},
  article = {arXiv preprint arXiv:2408.07009},
  year = {2024}
  }

Conferences

• 

  ReVersion: Diffusion-Based Relation Inversion from Images
  Ziqi Huang, Tianxing Wu, Yuming Jiang, Kelvin C.K. Chan, Ziwei Liu
  SIGGRAPH Asia, 2024
  

  • [PDF]
  • [Code]
  • [Project Page]
  • [Video]
  • [BibTeX]

  @inproceedings{huang2024reversion,
  author = {Huang, Ziqi and Wu, Tianxiang and Jiang, Yuming and Chan, Kelvin C.K. and Liu, Ziwei},
  title = {ReVersion: Diffusion-Based Relation Inversion from Images},
  booktitle = {SIGGRAPH Asia},
  year = {2024}
  }

• 

  Instruct-Imagen: Image Generation with Multi-modal Instruction
  Hexiang Hu*, Kelvin C.K. Chan*, Yu-Chuan Su*, Wenhu Chen*, Yandong Li, Kihyuk Sohn, Yang Zhao,
  Xue Ben, Boqing Gong, William Cohen, Ming-Wei Chang, Xuhui Jia
  CVPR, 2024 (Oral)

  • [PDF]
  • [Project Page]
  • [BibTeX]

  @inproceedings{hu2024instruct, 
  author = {Hu, Hexiang and Chan, Kelvin C.K. and Su, Yu-Chuan and Chen, Wenhu and Li, Yandong and Sohn, Kihyuk and Zhao, Yang and Ben, Xue and Gong, Boqing and Cohen, William and Chang, Ming-Wei and Jia, Xuhui},
  title = {Instruct-Imagen: Image Generation with Multi-modal Instruction},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year = {2024}
  }

• 

  Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
  Kelvin C.K. Chan, Yang Zhao, Xuhui Jia, Ming-Hsuan Yang, Huisheng Wang
  CVPR, 2024
  

  • [PDF]
  • [BibTeX]

  @inproceedings{chan2024subject, 
  author = {Chan, Kelvin C.K. and Yang, Zhao and Jia, Xuhui and Yang, Ming-Hsuan and Wang, Huisheng},
  title = {Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year = {2024}
  }

• 

  Dual Associated Encoder for Face Restoration
  Yu-Ju Tsai, Yu-Lun Liu, Lu Qi, Kelvin C.K. Chan, Ming-Hsuan Yang
  ICLR, 2024
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{zhou2023propainter,
  title={Dual Associated Encoder for Face Restoration},
  author={Tsai, Yu-Ju Tsai and Liu, Yu-Lun and Qi, Lu and Chan, Kelvin C.K. and Yang, Ming-Hsuan},
  booktitle={International Conference on Learning Representations},
  year={2024}
  }

• 

  ProPainter: Improving Propagation and Transformer for Video Inpainting
  Shangchen Zhou, Chongyi Li, Kelvin C.K. Chan, Chen Change Loy
  ICCV, 2023
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{zhou2023propainter,
  title={ProPainter: Improving Propagation and Transformer for Video Inpainting},
  author={Zhou, Shangchen and Li, Chongyi and Chan, Kelvin C.K. and Loy, Chen Change},
  booktitle={Proceedings of IEEE International Conference on Computer Vision},
  year={2023}
  }

• 

  Collaborative Diffusion for Multi-Modal Face Generation and Editing
  Ziqi Huang, Kelvin C.K. Chan, Yuming Jiang, Ziwei Liu,
  CVPR, 2023
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [Video]
  • [BibTeX]

  @inproceedings{huang2023collaborative,
  title={Collaborative Diffusion for Multi-Modal Face Generation and Editing},
  author={Huang, Ziqi and Chan, Kelvin C.K. and Jiang, Yuming and Liu, Ziwei},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2023}
  }

• 

  Exploring CLIP for Assessing the Look and Feel of Images
  Jianyi Wang, Kelvin C.K. Chan, Chen Change Loy
  AAAI, 2023
  

  • [PDF]
  • [Code]
  • [BibTeX]

  @inproceedings{wang2023exploring,
  title={Exploring CLIP for Assessing the Look and Feel of Images},
  author={Wang, Jianyi and Chan, Kelvin C.K. and Loy, Chen Change},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2023}
  }

• 

  

  Towards Robust Blind Face Restoration with Codebook Lookup TransFormer
  Shangzhou Zhou, Kelvin C.K. Chan, Chongyi Li, Chen Change Loy
  NeurIPS, 2022
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [Video]
  • [BibTeX]

  @inproceedings{zhou2022codeformer,
  title={Towards Robust Blind Face Restoration with Codebook Lookup TransFormer},
  author={Zhou, Shangchen and Chan, Kelvin C.K. and Li, Chongyi and Loy, Chen Change},
  booktitle={Neural Information Processing Systems},
  year={2022}
  }

• 

  RealBasicVSR: Investigating Tradeoffs in Real-World Video Super-Resolution
  Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
  CVPR, 2022
  

  • [PDF]
  • [Code]
  • [BibTeX]

  @inproceedings{chan2022investigating,
  author = {Chan, Kelvin C.K. and Zhou, Shangchen and Xu, Xiangyu and Loy, Chen Change},
  title = {Investigating Tradeoffs in Real-World Video Super-Resolution},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year = {2022}
  }
  

• 

  BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
  Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
  CVPR, 2022
  Champions , NTIRE 2021 Challenges on Video Restoration and Enhancement
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{chan2022basicvsrplusplus,
  author = {Chan, Kelvin C.K. and Zhou, Shangchen and Xu, Xiangyu and Loy, Chen Change},
  title = {BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year = {2022}
  }

• 

  BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
  Kelvin C.K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
  CVPR, 2021
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{chan2021basicvsr,
  title={BasicVSR: The search for essential components in video super-resolution and beyond},
  author={Chan, Kelvin C.K. and Wang, Xintao and Yu, Ke and Dong, Chao and Loy, Chen Change},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2021}
  }

• 

  

  GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
  Kelvin C.K. Chan, Xintao Wang, Xiangyu Xu, Jinwei Gu, Chen Change Loy
  CVPR, 2021 (Oral)
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{chan2021glean,
  title={GLEAN: Generative latent bank for large-factor image super-resolution},
  author={Chan, Kelvin C.K. and Wang, Xintao and Xu, Xiangyu and Gu, Jinwei and Loy, Chen Change},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2021}
  }

• 

  Robust Reference-based Super-Resolution via C²-Matching
  Yuming Jiang, Kelvin C.K. Chan, Xintao Wang, Chen Change Loy, Ziwei Liu
  CVPR, 2021
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [Dataset]
  • [BibTeX]

  @inproceedings{jiang2021robust,
  title={Robust Reference-based Super-Resolution via C2-Matching},
  author={Jiang, Yuming and Chan, Kelvin C.K. and Wang, Xintao and Loy, Chen Change and Liu, Ziwei},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2021}
  }

• 

  Understanding Deformable Alignment in Video Super-Resolution
  Kelvin C.K. Chan*, Xintao Wang*, Ke Yu, Chao Dong, Chen Change Loy
  AAAI, 2021
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{chan2020understanding,
  title={Understanding deformable alignment in video super-resolution},
  author={Chan, Kelvin C.K. and Wang, Xintao and Yu, Ke and Dong, Chao and Loy, Chen Change},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2020}
  }

• 

  EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
  Xintao Wang, Kelvin C.K. Chan, Ke Yu, Chao Dong, Chen Change Loy
  CVPRW, 2019
  Champions , NTIRE 2019 Challenges on Video Restoration and Enhancement
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{wang2019edvr,
  title={EDVR: Video Restoration with Enhanced Deformable Convolutional Networks},
  author={Wang, Xintao and Chan, Kelvin C.K. and Yu, Ke and Dong, Chao and Change Loy, Chen},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2019}
  }

Journals

• 

  Exploiting Diffusion Prior for Real-World Image Super-Resolution
  Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin C.K. Chan, Chen Change Loy
  IJCV, 2024
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @article{wang2024exploiting,
  author = {Wang, Jianyi and Yue, Zongsheng and Zhou, Shangchen and Chan, Kelvin C.K. and Loy, Chen Change},
  title = {Exploiting Diffusion Prior for Real-World Image Super-Resolution},
  article = {International Journal of Computer Vision},
  year = {2024}
  }

• 

  Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning
  Yihao Liu, Hengyuan Zhao, Kelvin C.K. Chan, Xintao Wang, Chen Change Loy, Yu Qiao, Chao Dong
  Computational Visual Media, 2024
  

  • [PDF]
  • [Video]
  • [BibTeX]

  @article{liu2024temporally,
  title={Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning},
  author={Liu, Yihao and Zhao, Hengyuan and Chan, Kelvin C.K. and Wang, Xintao and Loy, Chen Change and Qiao, Yu and Dong, Chao},
  journal={Computational Visual Media},
  year={2024}
  }

• 

  Reference-based Image and Video Super-Resolution via C2-Matching
  Yuming Jiang, Kelvin C.K. Chan, Xintao Wang, Chen Change Loy, Ziwei Liu
  TPAMI, 2023
  

  • [PDF]
  • [BibTeX]

  @article{jiang2023reference,
  title={Reference-based Image and Video Super-Resolution via C2-Matching},
  author={Jiang, Yuming and Chan, Kelvin C.K. and Wang, Xintao and Loy, Chen Change and Liu, Ziwei},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2023}
  }

• 

  

  GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution and Beyond
  Kelvin C.K. Chan, Xiangyu Xu, Xintao Wang, Jinwei Gu, Chen Change Loy
  TPAMI, 2022
  

  • [PDF]
  • [Code]
  • [BibTeX]

  @article{chan2022glean,
  title={GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution and Beyond},
  author={Chan, Kelvin C.K. and Xu, Xiangyu and Wang, Xintao and Gu, Jinwei and Loy, Chen Change},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2022}
  }

Preprints

• 

  Identity Encoder for Personalized Diffusion
  Yu-Chuan Su, Kelvin C.K. Chan, Yandong Li, Yang Zhao, Han Zhang, Boqing Gong, Huisheng Wang, Xuhui Jia
  arXiv preprint arXiv:2304.07429
  

  • [PDF]
  • [BibTeX]

  @article{su2023identity,
  author = {Su, Yu-Chuan and Chan, Kelvin C.K. and Li, Yandong and Zhao, Yang and Zhang, Han and Gong, Boqing and Wang, Huisheng and Jia, Xuhui},
  title = {Identity Encoder for Personalized Diffusion},
  article = {arXiv preprint arXiv:2304.07429},
  year = {2023}
  }

• 

  Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models
  Xuhui Jia*, Yang Zhao*, Kelvin C.K. Chan*, Yandong Li, Han Zhang, Boqing Gong, Tingbo Hou,
  Huisheng Wang, Yu-Chuan Su
  arXiv preprint arXiv:2304.02642
  

  • [PDF]
  • [BibTeX]

  @article{jia2023taming,
  author = {Jia, Xuhui and Zhao, Yang and Chan, Kelvin C.K. and Li, Yandong and Zhang, Han and Gong, Boqing and Hou, Tingbo and Wang, Huisheng and Su, Yu-Chuan},
  title = {Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion},
  article = {arXiv preprint arXiv:2304.02642},
  year = {2023}
  }

• 

  On the Generalization of BasicVSR++ to Video Deblurring and Denoising
  Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
  arXiv preprint arXiv:2204.05308
  

  • [PDF]
  • [Code]
  • [BibTeX]

  @article{chan2022generalization,
  author = {Chan, Kelvin C.K. and Zhou, Shangchen and Xu, Xiangyu and Loy, Chen Change},
  title = {On the Generalization of BasicVSR++ to Video Deblurring and Denoising},
  article = {arXiv preprint arXiv:2110.04562},
  year = {2022}
  }

Selected Awards

---

Academic Services

---