Peng-Tao Jiang
vivo researcher
School : Nankai University
Email : pt.jiang [at] vivo.com
Email : pt.jiang [at] mail.nankai.edu.cn
Github     Google Scholar

Biography

Research Interests

  • Universal scene parsing and understanding: DepthMaster (arXiv 2024), IPSeg (IJCV), TSP6K (CVPR 2024)
  • Unified architecture for dense prediction: MLoRE (CVPR 2024), TaskDiffusion (ICLR 2025)
  • Mobile image enhancement: RRW (CVPR24), ConsisSR (arxiv 2024), LAL (light adjustment, arxiv24)
  • Generative models and applications: B-TTDM (ECCV), DDAEBM (ICML24), ADM (ACM MM24)

    Experience

  • 2017-2022: Computer Science in Nankai University
  • 2022-2023: Post-doc Researcher in Zhejiang University
  • 2023-now: Researcher in vivo

    • Hiring

      We are hiring self-motivated research interns and full-time researchers. If you are interested in our group, please feel free to contact us.

Pre-print

Learning Adaptive Lighting via Channel-Aware Guidance
Qirui Yang*, Peng-Tao Jiang*#, Hao Zhang, Jinwei Chen, Bo Li, Huanjing Yue, Jingyu Yang#
arxiv, 2024
[PDF] [CODE]
ConsisSR: Delving Deep into Consistency in Diffusion-based Image Super-Resolution
Junhao Gu*, Peng-Tao Jiang*#, Hao Zhang, Mi Zhou, Jinwei Chen, Wenming Yang#, Bo Li
arxiv, 2024
[PDF] [CODE]
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation
Ziyang Song, Zerong Wang, Bo Li, Hao Zhang, Ruijie Zhu, Li Liu, Peng-Tao Jiang#, Tianzhu Zhang#
arxiv, 2024
[PDF] [CODE]
Towards Natural Image Matting in the Wild via Real-Scenario Prior
Ruihao Xia, Yu Liang, Peng-Tao Jiang#, Hao Zhang, Qianru Sun, Yang Tang#, Bo Li, Pan Zhou
arxiv, 2024
[PDF] [CODE]
Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation
Peng-Tao Jiang*, Yuqi Yang*
arXiv, 2023
[PDF] [CODE]

Selected Publications

* denotes equal contribution. # denotes the correspond authors.
Multi-Task Dense Predictions via Unleashing the Power of Diffusion
Yuqi Yang*, Peng-Tao Jiang*, Qibin Hou#, Hao Zhang, Jinwei Chen, Bo Li
International Conference on Learning Representations(ICLR), 2025
[PDF] [CODE]
Beta-Tuned Timestep Diffusion Model
Tianyi Zheng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang#, Bo Li#
European Conference on Computer Vision(ECCV), 2024
[PDF] [CODE]
Towards Training-free Open-world Segmentation via Image Prompt Foundation Models
Lv Tang*, Peng-Tao Jiang*, Haoke Xiao*, Bo Li#
International Journal of Computer Vision(IJCV), 2024
[PDF] [CODE]
Improving Adversarial Energy-Based Model via Diffusion Process
Cong Geng, Tian Han, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Søren Hauberg, Bo Li
International Conference on Machine Learning(ICML), 2024
[PDF] [CODE]
Revisiting Single Image Reflection Removal In the Wild
Yurui Zhu, Xueyang Fu, Peng-Tao Jiang, Hao Zhang, Qibin Sun, Jinwei Chen, Zheng-Jun Zh, Bo Li
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2024
[PDF] [CODE]
Multi-Task Dense Prediction via Mixture of Low-Rank Experts
Yuqi Yang*, Peng-Tao Jiang*, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2024
[PDF] [CODE]
Traffic Scene Parsing through the TSP6K Dataset
Peng-Tao Jiang*, Yuqi Yang*, Yang Cao, Qibin Hou, Ming-Ming Cheng, Chunhua Shen
IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2024
[PDF] [CODE] [DATASET(password:Wi9qFT)]

Professional Activities

  • Reviewer for TPAMI, TIP, IJCV, IJCAI, IJAC, NeurIPS, CVPR, ICCV, ICML, AAAI, PRCV