LAMLAU
profile photo

Lin Liu

Currently, I am a Senior Reseacher in Huawei CBG AI Lab, leading a small group that mainly works on AIGC. Before that, I obtained PhD degree at University of Science and Technology of China (USTC) and Shanghai AI Laboratory. During my studied, I had internship experience at the Noah's Ark Lab (supervised by Jianzhuang Liu), ByteDance (supervised by Qiubo Chen), and Tencent (supervised remotely by Quande Liu). I work closely with Shanxin Yuan, Xu Jia, Lingxi Xie, Mingming Zhao, and Prof. Qi Tian.

If you are interested in intern/full-time positions of our group or any other collaboration with me, welcome to contact me via email. (如果对来我们团队实习或全职工作感兴趣,欢迎发送邮件联系我)

Github  /  Google Scholar  /  Zhi Hu (知乎)

Education

  • 2022 - 2024 Graduate student (PhD), Department of Electronic Engineering and Information Science, USTC (中国科学技术大学), supervised by Qi Tian, Yanfeng Wang, and Houqiang Li.
  • 2019 - 2022 Graduate student (Master), Department of Electronic Engineering and Information Science, USTC (中国科学技术大学), supervised by Qi Tian, Wengang Zhou and Houqiang Li.
  • 2015 - 2019 Undergraduate student, Department of Information Security from USTC (中国科学技术大学), supervised by Qiang Ling.
  •   News

  • Feb.2024 - One paper has been accepted by TMM 2024 !
  • Nov.2022 - One paper has been accepted by AAAI 2023 !
  • Nov.2022 - One paper has been accepted by TCSVT 2022 !
  • Apr.2022 - We get the 5th place in the Night Photography Rendering Challenge and 3rd place in the HDR Challenge in NTIRE 22 !
  • Dec.2021 - One paper has been accepted by AAAI 2022 !
  • Sep.2021 - One paper has been accepted by TPAMI 2021 !
  • Aug.2021 - We take the second place on ByteDance Camp 2021.
  • Oct.2020 - I obtain the National Scholarship of China for guaduate students.
  • Sep.2020 - One paper has been accepted by NeurIPS 2020 !
  • Sep. 2020 - I join EI Innovation Lab, Cloud BU, Huawei as a student research intern.
  • Jul. 2020 - One paper has been accepted by ECCV 2020.
  • Feb. 2020 - One paper has been accepted by CVPR 2020.
  • Dec. 2019 - Our image demoireing algorithm obtains a patent.
  • Jun. 2019 - I obtain the excellent graduation thesis price of the USTC !
  • Jan. 2019 - I join Huawei Noah's Ark Lab as a research intern.
  • Publications

    My research interests include: 1) AIGC, 2) low-level vision and computational photography, 3) image/video or data compression, 4) Post-training of NLP, and 5) Neural radiance fields (NeRF).

    Arxiv Papers

    RASA: Replace Anyone, Say Anything – A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing
    Tianrui Pan*, Lin Liu✉, Jie Liu✉, Xiaopeng Zhang, Jie Tang, Gangshan Wu, Qi Tian
    arXiv preprint, 2025
    [paper] [project]

    Text-Animator: Controllable Visual Text Video Generation
    Lin Liu, Quande Liu, Shengju Qian, Yuan Zhou, Wengang Zhou, Houqiang Li, Lingxi Xie, Qi Tian
    arXiv preprint, 2024
    [paper] [project]
    Innovative framework for generating videos with dynamic visual text using text embedding injection and motion control modules

    Exploring Effective Mask Sampling Modeling for Neural Image Compression
    Lin Liu, Mingjie Zhao, Shanxin Yuan, Wei Lyu, Wengang Zhou, Houqiang Li, Yanfeng Wang, Qi Tian
    arXiv preprint, 2023
    [paper] [code (coming soon)]

    Conference Papers

    Low-Light Video Enhancement with Synthetic Event Guidance
    Lin Liu, Junfeng An, Jianzhuang Liu, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Yanfeng Wang, Qi Tian
    AAAI Conference on Artificial Intelligence (AAAI), 2023
    [paper] [code]

    TAPE: Task-Agnostic Prior Embedding for Image Restoration
    Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian
    European Conference on Computer Vision (ECCV), 2022
    [paper] [project (code)]

    SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
    Lin Liu, Shanxin Yuan, Jianzhuang Liu, Xin Guo, Youliang Yan, Qi Tian
    AAAI Conference on Artificial Intelligence (AAAI), 2022
    [paper]

    Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs
    Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian
    Neural Information Processing Systems (NeurIPS), 2020
    [paper] [code]

    Wavelet-Based Dual-Branch Network for Image Demoireing
    Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian
    European Conference on Computer Vision (ECCV), 2020
    [paper] [code]

    Joint Demosaicing and Denoising with Self Guidance
    Lin Liu, Xu Jia, Jianzhuang Liu, Qi Tian
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    [paper] [code]

    Journal Papers

    Video Demoireing with Deep Temporal Color Embedding and Video-Image Invertible Consistency
    Lin Liu, Junfeng An, Shanxin Yuan, Wengang Zhou, Houqiang Li, Yanfeng Wang, Qi Tian
    IEEE Transactions on Multimedia, 2023
    [paper (coming soon)]

    Learning Frequency Domain Priors for Image Demoireing
    Bolun Zheng, Shanxin Yuan, Chenggang Yan, Xiang Tian, Jiyong Zhang, Yaoqi Sun, Lin Liu, Ales Leonardis, Greg Slabaugh
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
    [paper] [code]

    Projects or Competitions

  • 2022, the 5th place, in the Night Photography Rendering Challenge in NTIRE 22
  • 2022, the 3rd place, in the HDR Challenge in NTIRE 22
  • 08/2021, the 2nd place, Low light video enhancement using 3D curve estimation at ByteDance Summer Camp 2021 .
  • 10/2022, the 4th place, FlowMat transformer at the 3th Wireless AI Competition .
  • Talks

  • 06/2021, "Challenges and Solutions for Intelligent Image Restoration" at NTIRE 2021 .
  • Abstract: In recent years, with the development of deep learning, image restoration and enhancement, such as image denoising and image super-resolution, have attracted more and more attention. This talk will focus on the challenges faced by image restoration and propose some solutions: 1) For the problem that real data is difficult to obtain, we introduce methods of synthesizing more real data, self-supervised learning, and fine-tuning using pre-trained models. 2) For the existing models have limited in mining useful information, we first introduce the concept of ‘guidance restoration’, then introduce some self-guidance and external-guidance methods. 3) At last, we introduce some video or burst methods for image restoration.

    Services

  • Reviewers of ICCV2021, TOMM2021, CVPR2022, ECCV2022,AAAI2023, CVPR2023

  • Awards

    2022.10   Suzhou Yucai Scholarship (苏州育才奖学金)

    2019.09   National Network Security Scholarship (国家网络安全奖学金) (link)

    2018.09   National Scholarship (国家奖学金)  (highest national wide scholarship for students in China)

    2019.09   Outstanding Graduate Student of Anhui Province (安徽省优秀毕业生)

    2017.09   Scholarship of Institute of electronics, Chinese Academy of Sciences (中国科学院电子所奖学金)

    2017.10   中国科学技术大学机器人竞赛,第二名

    -->