Xinqi Lin (林心淇)

I am a second-year graduate student at XPixelGroup, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences. I am supervised by Prof. Chao Dong. I also work closely with Dr. Jinjin Gu.

Prior to that, I received my B.Eng. from the Tianjin University (TJU) in 2023.

My current research interest mainly lies in image restoration, image super-resolution.

CV  /  Google Scholar  /  Github
Email: xqlin0613 [at] gmail [dot] com

[2024.07]    One paper to appear in ECCV 2024. See you in Milan.
[2023.09]    I reached my first 1,000 stars on GitHub!
[2023.07]    I graduate and receive my Bachelor's degree from Tianjin University.

*: Equal Contribution, †: Corresponding Author

We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework.

We propose a simple and effective method, HYPIR, to achieve a good balance between restoration quality, fidelity, and speed.

We introduced new real-world datasets named FOS with a taxonomy of "Full, Occluded, and Side" faces from mainly video frames to study the applicability of current methods on videos.

We present VEnhancer, a generative space-time enhancement framework that improves the existing text-to-video results by adding more details in spatial domain and synthetic detailed motion in temporal domain.

AdaptBIR aims to help diffusion models get their footing in the low-level vision field, solving the pain point of insufficient fidelity.

Template from JonBarron