profile photo

Lin Liu

Currently, I am a joint PhD student at University of Science and Technology of China (USTC) and Shanghai AI Laboratory. I was a master student in the School of Information of Science and Technology, University of Science and Technology of China(USTC). Previously, I spent 8 months at the Noah's Ark Lab, Huawei Tech as a research intern, working with Prof. Jianzhuang Liu. I work closely with Shanxin Yuan, Xu Jia, Lingxi Xie, Mingming Zhao, and Prof. Qi Tian.

Github  /  Google Scholar  /  Zhi Hu (知乎)


  • Sep. 2022 - Now 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.
  • Sep. 2019 - Jun. 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.
  • Sep. 2015 - Jun. 2019 Undergraduate student, Department of Information Security from USTC (中国科学技术大学), supervised by Qiang Ling.
  •   News

  • 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.
  • Projects or Competitions

  • 08/2021, the second 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.


    I'm interested in low-level vision of computer vision and computational photography.

    Conference Papers:

  • Low-Light Video Enhancement with Synthetic Event Guidance

    (AAAI), 2023
    Lin Liu, Junfeng An, Jianzhuang Liu, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Yanfeng Wang, Qi Tian

    In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages.

    PDF (Arxiv) /  Project Page (Comming soon!) /  Code (MindSpore) (Comming soon!)  / 

  • TAPE: Task-Agnostic Prior Embedding for Image Restoration

    (ECCV), 2022
    Lin Liu, Lingxi Xie, Xiaopeng Zhang, Shanxin Yuan, Xiangyu Chen, Wengang Zhou, Houqiang Li, Qi Tian

    In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer. Our approach, named Task-Agnostic Prior Embedding (TAPE), consists of three stages, namely, task-agnostic pre-training, task-agnostic fine-tuning, and task-specific fine-tuning, where the first one embeds prior knowledge about natural images into the transformer and the latter two extracts the knowledge to assist downstream image restoration.

    PDF /  Project Page  /  Code  / 

  • SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

    (AAAI), 2022
    Lin Liu, Shanxin Yuan, Jianzhuang Liu, Xin Guo, Youliang Yan, Qi Tian

    We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames.

    PDF /  Codes (Release soon! )  /  Project page

  • Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs

    Thirty-fourth Conference on Neural Information Processing Systems(NeurIPS), 2020
    Lin Liu, Shanxin Yuan, Jianzhuang Liu, Liping Bao, Gregory Slabaugh, Qi Tian

    We propose a self-adaptive learning method for image demoiréing, which uses an additional input (defocused moiré-free image) to help remove moiré patterns from the focused moiré image.

    PDF /  Codes  /  Project page

  • Wavelet-Based Dual-Branch Networkfor Image Demoireing

    European Conference on Computer Vision(ECCV), 2020
    Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Ales Leonardis, Wengang Zhou, Qi Tian

    We propose a novel wavelet-based and dual-branch neural network for image demoireing. Our network removes moire patterns in the wavelet domain to separate the frequencies of moire patterns from the image content.

    PDF /  Codes

  • Joint Demosaicing and Denoising with Self Guidance

    Conference on Computer Vision and Pattern Recognition(CVPR), 2020
    Lin Liu, Xu Jia, Jianzhuang Liu, Qi Tian

    We propose a novel self-guidance network (SGNet) with density-map guidance and green-channel guidance for joint demosaicing and denoising (JDD). And it works well in super-resolution too.

    PDF /  Codes

  • Journal Papers:

  • Learning Frequency Domain Priors for Image Demoireing

    IEEE Transactions on Pattern Analysis and Machine Intelligence ( TPAMI ), 2021
    Bolun Zheng; Shanxin Yuan; Chenggang Yan; Xiang Tian; Jiyong Zhang; Yaoqi Sun; Lin Liu ; Ales Leonardis; Greg Slabaugh

    In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing.

    PDF /  Codes  / 

  • HRInversion: High-Resolution GAN Inversion for Cross-Domain Image Synthesis

    ( TCSVT ), 2022
    Peng Zhou; Lingxi Xie; BingBing Ni; Lin Liu ; Qi Tian

    In this paper, we use the GAN inversion method for cross-domain image synthesis.

    PDF /  Codes / 
  • 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