Tian Ye

Tian Ye

CV Researcher@HKUST(GZ)

👋 About Me

I am Tian Ye, a PhD student at HKUST’s ROAS Thrust and Co-founder of MeissonFlow Research. I am fortunate to be supervised by Prof. Lei Zhu and Prof. Kan, Ge Lin. During my undergraduate studies, I had the honor of being supervised by and collaborating with Prof. Erkang Chen and Prof. Yun Liu. Currently, I am working closely with Dr. Hongwei Yi (Founding Scientist at Hedra) to explore and develop Foundational Video Generation Models (e.g., Magic 1-For-1, MagicInfinite).

🔬 Research Interests

My research focuses on two key areas:
🎨

AIGC Technology

Supporting the art creation industry and digital asset generation through advances in AIGC (Artificial Intelligence Generated Content) technology

📸

Visual Quality

Exploring visual challenges in photography to create images with superior quality.

📰 News

  • [2025-03] We are pleased to announce the release of MagicInfinite (Character-3 Model of Hedra Inc.). Now you can fastly generate infinite talking videos with your words and voice!
  • [2025-02] 3 Papers are accepted by CVPR 2025.
  • [2025-02] We are pleased to announce the release Magic 1-For-1, a SOTA, 4-step image-to-video diffusion model, along with our technical report.
  • [2025-01] I am honored to be selected as a speaker at KAUST Rising Stars in AI Symposium 2025!! Thank you KAUST for the opportunity!
  • [2025-01] Meissonic is accepted by ICLR 2025🎉.
  • [2024-12] 4 Papers are accepted by AAAI 2025.
  • [2024-11] I am honored to be selected as a Outstanding Reviewer for BMVC 2024！
  • [2024-11] We release Meissonic on HuggingFace🎉, Meissonic-1B is the first SDXL level, high-resolution non-AR T2I model!!
  • [2024-09] 2 Papers are accepted by ECCV 2024.
  • [2024-06] 2 Papers are accepted by MICCAI 2024, and Segmamba is selected as a Spotlight presentation paper.

📝 Selected Papers

[🔥Talking Avatar Model🔥]🔥🔥🔥MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
Hongwei Yi*, Tian Ye*, Shitong Shao*, Xuancheng Yang*, Jiantong Zhao*, Hanzhong Guo*, Terrance Wang, Qingyu Yin, Zeke Xie, Lei Zhu, Wei Li, Michael Lingelbach, Daquan Zhou
Arxiv 2025
PDF | Project | Character-3 Model of Hedra Inc.
▶️ Watch Demo

[🔥Foundational Generation Model🔥]🔥🔥🔥Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Jinbin Bai*, Tian Ye*, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan
ICLR 2025 The first SDXL Level, High-Resolution Non-AR T2I Model!
PDF | Project | HF Model | Adina Yakup@Twitter

[Generative Image Enhancement] AGLLDiff : Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
Yunlong Lin*, Tian Ye*, Sixiang Chen*, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu and Xinghao Ding
AAAI 2025
PDF | Project

[Real-world Restoration] PromptHaze: Prompting Real-world Dehazing via Depth Anything Model
Tian Ye, Sixiang Chen, Haoyu Chen, Wenhao Chai, Jingjing Ren, Zhaohu Xing, Wenxue Li, Lei Zhu
AAAI 2025

[Generative Image Restoration] Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint
Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, and Lei Zhu
ECCV 2024
PDF | Project | code

[Video Restoration] Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization
Jingjing Ren, Haoyu Chen, Tian Ye, Hongtao Wu and Lei Zhu
IJCV 2024
PDF

[Medical Image Seg] SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation
Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu and Lei Zhu
MICCAI 2024 Selected as a Spotlight presentation paper (about 20 of 2,869 valid submissions) and Early Accepted by MICCAI. Don't need rebuttal!
PDF | code

[Generative Model For IR] Learning Diffusion Texture Priors for Image Restoration
Tian Ye, Sixiang Chen, Wenhao Chai, Zhaohu Xing, Jing Qin, Ge Lin, Lei Zhu.
CVPR Highlight 2024 Selected as a Highlight presentation paper (324 of 11,532 valid submissions).
PDF | CVPR Poster

[Generative Model For IR] VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook
Wenbin Zou, Hongxia Gao, Tian Ye, Liang Chen, Weipeng Yang, Shasha Huang, Hongsheng Chen, Sixiang Chen
AAAI 2024
PDF | Code

[Image Restoration] Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
Sixiang Chen*,Tian Ye*, Jinbin Bai, Jun Shi, Erkang Chen, Lei Zhu.
ICCV 2023
PDF | Code | Project

[Generative Model For IR] Adverse Weather Removal with Codebook Priors
Tian Ye*, Sixiang Chen*, Jinbin Bai*, Shi Jun, Chenghao Xue, Jingjia Jiang, Junjie Yin, Erkang Chen, Yun Liu.
ICCV 2023
PDF | Code

[Image Restoration] Uncertainty-Driven Dynamic Degradation Perceiving and Background Modeling for Efficient Single Image Desnowing
SiXiang Chen*, Tian Ye*, Chenghao Xue, Haoyu Chen, Yun Liu, Erkang Chen, Lei Zhu
ACM Multimedia (ACM MM) 2023
PDF | Code

[Image Restoration] Perceiving and Modeling Density for Image Dehazing
Tian Ye*, Yunchen Zhang*, Mingchao Jiang*, Liang Chen, Yun Liu, Erkang Chen.
ECCV Oral, 2022. Selected as a Oral presentation paper (Top 2.7%, 158 of 5,803 valid submissions).
PDF | Code

Mentoring

I am very lucky to work with the following talented students:

  • [Heming Li], RA@HKUST(GZ), B.S.@CUHK
  • [Song Fei], Mphil Student@HKUST(GZ).
  • [Haoxuan Feng], Mphil Student@HKUST(GZ).
  • [Chenghao Xue], Now MSc Student@UC Davis.
  • [Jingxia Jiang], Now PhD Student@NC State.

🎖 Competitions & Awards & Presentations

💬 Academic Services

  • Conference Reviewer: ACCV 2022&2024, WACV 2023&2024, BMVC 2023&2024, AAAI 2022&2023&2024&2025, ICCV 2023, CVPR 2024, ECCV 2024, ACM MM 2024, NeurIPS 2024, ICLR 2025, ICML 2025.

  • Workshop Competition Organizer: LOVEU@CVPR 2024

  • Journal Reviewer:

    International Journal of Computer Vision

    IEEE Signal Processing Letter

    IEEE Journal of Oceanic Engineering

📖 Educations&Experience

  • Aug’2024-Present: PhD Student, The Hong Kong University of Science and Technology, Guangzhou.

  • Jun’2023-Jul’2024: Research Assistant, The Hong Kong University of Science and Technology, Guangzhou.

  • Sep’2019-Jul’2023: B.Eng (Telecommunication Engineering), Jimei University, Xiamen.