Xiefan Guo

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

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
Xiefan Guo, Xinzhu Ma, Haiyu Zhang, and Di Huang
In: The 44th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 3-7, 2026, Denver, USA
Paper

Towards Accurate Quantization for Large Vision-Language Models via Zeroth-Order Gradient Optimization and
Sectioned Logarithmic Quantizer
Jiayi Zhang, Jiaxin Chen, Xiefan Guo, Xin Tong, and Di Huang
In: The 51st IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 4-8, 2026, Barcelona, Spain
Paper

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), October 19-23, 2025, Hawaii, USA
Paper / arXiv / Code / Project / Poster

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
Jinjin Zhang, Qiuyu Huang, Junjie Liu, Xiefan Guo, and Di Huang
In: The 43rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 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), June 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), June 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), June 19-24, 2022, New Orleans, USA
Paper / 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), October 11-17, 2021, Montreal, Canada (Virtual)
Paper / arXiv / Code / Slide / Poster

Video Diffusion Model for Human Videos with Moving Background
Alibaba TongYi Lab
A human video diffusion model is capable of synthesizing photorealistic human movements in a moving background.
Tech Report / Project

DreaMoving: A Human Video Generation Framework based on Diffusion Models
DreaMoving Team, Alibaba TongYi Lab
A diffusion-based controllable video generation framework to produce high-quality customized human videos.
Tech Report / Code / Project / ModelScope / Hugging Face

Portrait Skin Retouching
Alibaba DAMO Academy
A portrait skin retouching model for skin homogenization, blemish removal and lightening.
ModelScope