Xiefan Guo Portrait

Xiefan Guo

Ph.D. Candidate

Beihang University (BUAA)

Email: guoxiefan@gmail.com

Google Scholar GitHub ResearchGate Twitter

I am a Ph.D. student at the School of Computer Science and Engineering, Beihang University (BUAA), supervised by Prof. Di Huang. My research interests focus on Computer Vision, Generative AI, and Diffusion models. Before that, I received my master degree from the School of Computer Science and Engineering, Beihang University (BUAA), China, in Jan. 2023 and B.E degree from the College of Intelligence and Computing, Tianjin University (TJU), China, in Jul. 2020. I interned at Shanghai AI Laboratory, Alibaba TongYi Lab and Alibaba DAMO Academy.

Preprints

Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
Jinjin Zhang, Qiuyu Huang, Junjie Liu, Xiefan Guo, and Di Huang
In: arXiv:2506.01331, Technical Report, 2025
[Paper] [Code] [Dataset]

I4VGen: Image as Free Stepping Stone for Text-to-Video Generation
Xiefan Guo, Jinlin Liu, Miaomiao Cui, Liefeng Bo, and Di Huang
In: arXiv:2406.02230, Technical Report, 2024
[Paper] [Code] [Project]

DreaMoving: A Human Video Generation Framework based on Diffusion Models
DreaMoving Team: Mengyang Feng, Jinlin Liu, Kai Yu, Yuan Yao, Zheng Hui, Xiefan Guo, Xianhui Lin, et al.
In: arXiv:2312.05107, Technical Report, 2023
[Paper] [Code] [Project] [ModelScope] [Hugging Face]

View all publications

Publications

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
Xiefan Guo, Miaomiao Cui, Liefeng Bo, and Di Huang
In: The 20th IEEE International Conference on Computer Vision (ICCV), Oct. 19-23, 2025, Hawaii, USA
[Paper] [Code]

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
Jinjin Zhang, Qiuyu Huang, Junjie Liu, Xiefan Guo, and Di Huang
In: The 43nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 11-15, 2025, Nashville, USA
[Paper] [arXiv] [Code] [Dataset]

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
Xiefan Guo, Jinlin Liu, Miaomiao Cui, Jiankai Li, Hongyu Yang, and Di Huang
In: The 42nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 17-21, 2024, Seattle, USA
[Paper] [arXiv] [Code] [Project] [Slide] [Poster]

Leveraging Predicate and Triplet Learning for Scene Graph Generation
Jiankai Li, Yunhong Wang, Xiefan Guo, Ruijie Yang, and Weixin Li
In: The 42nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 17-21, 2024, Seattle, USA
[Paper] [arXiv] [Code]

ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo
Biwen Lei, Xiefan Guo, Hongyu Yang, Miaomiao Cui, Xuansong Xie, and Di Huang
In: The 40th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 19-24, 2022, New Orleans, USA
[Paper] [ModelScope] [Dataset]

Image Inpainting via Conditional Texture and Structure Dual Generation
Xiefan Guo, Hongyu Yang, and Di Huang
In: The 18th IEEE International Conference on Computer Vision (ICCV), Oct. 11-17, 2021, Montreal, Canada (Virtual)
[Paper] [arXiv] [Code] [Slide] [Poster]

View all publications

Honors & Awards

Beihang University

2023: Outstanding Freshman Scholarship for PhD Student

2022: Excellent Graduate Award

2022: Tansuo Award

2021: National Scholarship

Tianjin University

2020: Excellent Graduate Award

2019: National Scholarship

2018: Weichai Power Scholarship

ACM ICPC & CCPC

2018: Silver Medal, ACM International Collegiate Programming Contest (ACM-ICPC), Asia Regional Contest

2018: Silver Medal, China Collegiate Programming Contest (CCPC), Regional Contest

Professional Activities

Conference Reviewer:

CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR, AISTATS, ACM MM, ICMR, ECAI, BMVC, PRCV

Journal Reviewer:

TPAMI, TVCG, TCSVT, TMM, CVIU, FCS, J-STSP

News

(New) Jun. 2025

Our paper, titled “ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning” is accepted by ICCV 2025.

Feb. 2025

Our paper, titled “Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models” is accepted by CVPR 2025.

Jun. 2024

We release the official PyTorch implementation of I4VGen.

May 2024

Invited talk at Alibaba Cloud on InitNO, CVPR 2024.

Feb. 2024

Our paper, titled “InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization” is accepted by CVPR 2024.

Our paper, titled “Leveraging Predicate and Triplet Learning for Scene Graph Generation” is accepted by CVPR 2024.

Sep. 2023

I start my intern at Alibaba TongYi Lab.

Mar. 2022

Our paper, titled “ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo” is accepted by CVPR 2022.

Sep. 2021

I obtain China National Scholarship.

Jul. 2021

Our paper, titled “Image Inpainting via Conditional Texture and Structure Dual Generation” is accepted by ICCV 2021.

View all news