Hi, I’m Xuhan, a third-year Master’s student at the Visual-Information Intelligent Learning LAB at Peking University (PKU), where I am fortunate to be advised by Prof. Jian ZHANG. I am expected to graduate in June 2026.

Previously, I earned my Bachelor’s degree in Artificial Intelligence from the Dalian University of Technology, under the supervision of Prof. Xu JIA. My research interests include Low-level Vision, AIGC, and 3D Vision.

I am always open to academic and industry collaborations. Feel free to reach out for research discussions or potential partnerships!

Currently seeking Ph.D. (2026 Fall / 2027 Spring) or job opportunities(2026 June). Here is my CV.

🔥 News

  • 2025.06:  🎉 1 paper was accepted in ICME 2025 for oral presentation.
  • 2024.09:  🎉 Our “OmniSSR” was accepted in ECCV 2024 for oral presentation.
  • 2023.06:  🏆 We won the “NTIRE 2023 Challenge on 360deg Omnidirectional Image Super-Resolution track” championship.

📝 Publications

(*: indicates equal contribution; #: indicates corresponding author)

Preprint
sym

RealOSR: Latent Unfolding Boosting Diffusion-based Real-world Omnidirectional Image Super-Resolution

Xuhan Sheng*, Runyi Li*, Bin Chen, Weiqi Li, Xu Jiang, Jian Zhang#

Preprint 2025

  • A one-step denoising diffusion model with latent unfolding in the latent space for real-world 360° image super-resolution, achieving ×200 acceleration.

Paper

ICME 2025
sym

Label-guided Facial Retouching Reversion

Guanhua Zhao*, Yu Gu*, Xuhan Sheng, Yujie Hu, Jian Zhang#

ICME 2025, Oral Presentation

  • Proposed a facial retouching reversion algorithm capable of removing beautification effects such as “skin smoothing,” “eye enlargement,” and “face slimming.”

Paper

ECCV 2024
sym

OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model

Runyi Li*, Xuhan Sheng*, Weiqi Li, Jian Zhang#

ECCV 2024, Oral Presentation

  • A zero-shot framework that uses existing planar image diffusion super-resolution models (e.g., StableSR) for 360° image SR.

Paper | Project Page | GitHub

NTIRE 2023
sym

OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution

Xiaopeng Sun *, Weiqi Li*, Zhenyu Zhang, Qiufang Ma, Xuhan Sheng, et al.

CVPR Workshops 2023

  • The 🏆 champion solution for “NTIRE 2023 Challenge on 360deg Omnidirectional Image Super-Resolution track”.

Paper

📚 Educations

2023.09 - Now

Master Student, Peking University, VILLA Lab

Advisor: Prof. Jian ZHANG

2019.09 - 2023.09

Bachelor Student, Dalian University of Technology

Advisor: Prof. Xu JIA

😊 Hobbies

I love playing flutes (Irish flute, Boehm flute, Shakuhachi). I love Hatsune Miku. I am learning Cantonese.