Xin Jin

PhD student, Nankai University

Xin Jin (靳鑫) is a PhD student at Nankai University, advised by Prof. Ming-Ming Cheng. His research interests include computer vision and deep learning, particularly focusing on computational photography.

News

  • 2024/06 -- We present LE3D, enabling real-time rendering for HDR view synthesis!
  • 2024/01 -- The Few-shot RAW Image Denoising Track in MIPI 2024 has started!
  • 2023/12 -- A honor to co-organize the MIPI workshop @ CVPR2024 with NTU S-Lab!
  • 2023/12 -- We have released a extension version of our LED. Code is also released on Github!
  • 2023/07 -- The official code of Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising has been released on Github!
  • 2023/07 -- One paper, including LED, got accepted by ICCV 2023.
  • 2023/05 -- The official code of DNF: Decouple and Feedback Network for Seeing in The Dark has been released on Github!
  • 2023/03 -- Excited to announce one paper accepted by CVPR 2023 was selected as Highlight, 10% of accepted papers, 2.5% of submissions!
  • 2023/03 -- One paper got accepted by CVPR 2023.
  • 2023/01 -- Our paper was awarded oral presentation qualification by AAAI.
  • 2022/11 -- One paper got accepted by AAAI 2023.
  • 2022/04 -- I have won the third place in RAW Image Blind De-noising as the team leader in Megcup 2022!
  • 2022/04 -- Our team have won the third place in Night Photography Rendering Challenge, CVPRW 2022!
  • 2022/03 -- One paper got accepted by ICPR 2022 and selected as oral presentation.

Publications

* Eauql contribution. # Corresponding author. Representative papers are highlighted.

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
Xin Jin*, Pengyi Jiao*, Zheng-Peng Duan, Xingchao Yang, Chun-Le Guo, Bo Ren, Chongyi Li.
arxiv, 2024  
project / paper / code / bibtex
Make Explict Calibration Implicit: "Calibrate" Denoiser Instead of The Noise Model
This is an extension of our LED, ICCV 2023.
Xin Jin, Jia-Wen Xiao, Ling-Hao Han, Chun-Le Guo#, Xialei Liu, Chong-Yi Li, Ming-Ming Cheng#.
arxiv, 2023  
project / paper / code / bibtex
Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising
Xin Jin*, Jia-Wen Xiao*, Ling-Hao Han, Chun-Le Guo#, Ruixun Zhang, Xialei Liu, Chong-Yi Li.
ICCV, 2023  
project / paper / code / bibtex
DNF: Decouple and Feedback Network for Seeing in the Dark
Xin Jin*, Ling-Hao Han*, Zhen Li, Chun-Le Guo#, Zhi Chai, Chong-Yi Li.
CVPR, 2023, (Highlight)  
paper / code / bibtex
Underwater Ranker: Learn Which Is Better and How to Be Better
Chun-Le Guo*, Rui-Qi Wu*, Xin Jin, Ling-Hao Han, Zhi Chai, Wei-Dong Zhang, Chong-Yi Li#.
AAAI, 2023, (Oral)  
project / paper / code / dataset (pwd: nuin) / bibtex
A Novel Low-light Image Enhancement Algorithm Based On Information Assistance
Jiacen Guo, Xin Jin, Weilin Chen, Chao Wang#.
ICPR, 2022, (Oral)
paper / bibtex

Experience

Adobe
2024/06 - Present
San Jose CA, USA

Research Scientist Intern

Working with amazing researchers such as Simon Niklaus, Zhihao Xia and Jiawen Chen.

MIPI
2023/12 - 2024/06
Seattle WA, USA

Joint Organizer

Organized the MIPI workshop @ CVPR 2024 with Chen Change Loy, Jimmy S. Ren, Shangchen Zhou, etc. I lead the Few-shot RAW Image Denoising Track.

Megvii
2023/05 - 2024/06
Beijing, China

Research Scientist Intern

Worked with Xingchao Yang, where we worked on Burst Denoising and HDR view synthesis (LE3D).

Megvii
2022/05 - 2022/09
Beijing, China

Research Engineer Intern

Worked with Yuzhi Wang, where I came up with the idea of LED.

Competitions and Awards

Education

2022/09 - Present, I am a Ph.D student at College of Computer Science, Nankai University, under the supervision of Prof. Ming-Ming Cheng.

2018/09 - 2022/07, I was an undergraduate student at College of Software, Nankai University.

Contact

You are very welcome to contact me regarding my research. I typically respond within a few days.
I can be contacted directly at xjin [at] mail.nankai.edu.cn.