About Me

I am currently a fourth-year PhD student at The Hong Kong Polytechnic University (PolyU), supervised by Prof. Lei Zhang. I obtained my M.S. degree in 2022 and my B.S. degree in 2019, both from Northwestern Polytechnical University (NPU), where I was supervised by Prof. Yongqiang Zhao.

My research focuses on computational photography and generative models, with a particular interest in real-world image super-resolution. I enjoy discussions around visually grounded learning systems, practical restoration pipelines, and collaborative research opportunities.

First-Author Papers

CVPR 2026

VOSR: A Vision-Only Generative Model for Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Xiangtao Kong, Jixin Zhao, Shihao Wang, Lei Zhang

Paper | Code

A framework for native generative image restoration.

NeurIPS 2025

DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang

Paper | Code

How can DPO help real-world image super-resolution?

NeurIPS 2024

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, Lei Zhang

Paper | Code

High-quality and stable super-resolution in just one diffusion step, successfully deployed in OPPO Find X8 Pro.

CVPR 2024

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

Rongyuan Wu, Tao Yang, Lingchen Sun, Zhengqiang Zhang, Shuai Li, Lei Zhang

Paper | Code

Preserving semantic fidelity in real-world super-resolution with degradation-aware tag prompts.

Co-authored Papers

Generative Models

• Beyond External Guidance: Unleashing the Semantic Richness Inside Diffusion Transformers for Improved Training
  Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang, Ruibin Li, Yujing Sun, Shuaizheng Liu, Lei Zhang, arXiv 2026.
  Paper Code
• GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
  Zhengqiang Zhang, Rongyuan Wu, Lingchen Sun, Lei Zhang, NeurIPS 2025.
  Paper Code

Low-Level Vision

• Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
  Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang, Hongwei Yong, Lei Zhang, IEEE TIP 2026.
  Paper Code
• GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
  Qiaosi Yi, Shuai Li, Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Lei Zhang, CVPR 2026.
  Paper Code
• NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
  Xiangtao Kong, Rongyuan Wu, Shuaizheng Liu, Lingchen Sun, Lei Zhang, arXiv 2025.
  Paper Code
• One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
  Yujing Sun, Lingchen Sun, Shuaizheng Liu, Rongyuan Wu, Zhengqiang Zhang, Lei Zhang, NeurIPS 2025.
  Paper Code
• Fine-structure Preserved Real-World Image Super-Resolution via Transfer VAE Training
  Qiaosi Yi, Shuai Li, Rongyuan Wu, Lingchen Sun, Yuhui Wu, Lei Zhang, ICCV 2025.
  Paper Code
• Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
  Lingchen Sun, Rongyuan Wu, Zhiyuan Ma, Shuaizheng Liu, Qiaosi Yi, Lei Zhang, CVPR 2025.
  Paper Code
• Adversarial Diffusion Compression for Real-World Image Super-Resolution
  Bing Chen, Gehui Li, Rongyuan Wu, Xindong Zhang, Jie Chen, Jian Zhang, Lei Zhang, CVPR 2025.
  Paper Code
• Pixel-aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization
  Tao Yang, Rongyuan Wu, Peiran Ren, Xuansong Xie, Lei Zhang, ECCV 2024.
  Paper Code

3D Generation

• Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data
  Zhiyuan Ma, Xinyue Liang, Rongyuan Wu, Xiangyu Zhu, Zhen Lei, Lei Zhang, CVPR 2025.
  Paper Code

Awards

• NeurIPS 2025 Top Reviewer
• CVPR 2025 Outstanding Reviewer
• 1st Place, Quad-Bayer Re-mosaic and RGBW Sensor Re-mosaic Tracks, MIPI Challenge, ECCV Workshop, 2022
• National Scholarship, NPU, 2021

Services

• Conference Reviewer: CVPR, ICCV, ECCV, ICLR, NeurIPS, AAAI, ACM MM
• Journal Reviewer: IEEE TPAMI, IJCV, IEEE TIP