Yuandong Pu

Yuandong Pu

Auto-generated profile, based on publicly available information

Yuandong Pu

Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China

Research Focus & Metrics

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
XCXiangyu Chen
Xiangyu Chen
YLYihao Liu
Yihao Liu
YPYuandong Pu
Yuandong Pu
Wenlong ZhangWenlong Zhang
Wenlong Zhang
JZJiantao Zhou
Jiantao Zhou
CDChao Dong
Chao Dong
Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean restoration tasks, while their applicability to tasks with different target domains (e.g., image stylization) is limited. Methods like PromptGIP can handle multiple input-target domains but rely on the Masked Autoencoder (MAE) paradigm. Consequently, they are tied to the ViT architecture, resulting in suboptimal image reconstruction quality. In addition, these methods are sensitive to prompt image content and often struggle with low-frequency information processing. In this paper, we propose a Visual task Prompt-based Image Processing (VPIP) framework to overcome these challenges. VPIP employs visual task prompts to manage tasks with different input-target domains and allows flexible selection of backbone network suitable for general tasks. Besides, a new prompt cross-attention is introduced to facilitate interaction between the input and prompt information. Based on the VPIP framework, we train a low-level vision generalist model, namely GenLV, on 30 diverse tasks. Experimental results show that GenLV can successfully address a variety of low-level tasks, significantly outperforming existing methods both quantitatively and qualitatively. Codes are available at https://github.com/chxy95/GenLV.

9 November 2026
Verified
Conference Paper
Open access
KZKaiwen Zhu
Kaiwen Zhu
QZQuan-Sheng Zeng
Quan-Sheng Zeng
YPYuandong Pu
Yuandong Pu
SCShuo Cao
Shuo Cao
XLXiaohui Li
Xiaohui Li
YLYihao Liu
Yihao Liu