publications

2025

1. 

   POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction

   Songyan Zhang^*, Yongtao Ge^*, Jinyuan Tian^*, Guangkai Xu, Chen Lv, Hao Chen, and Chunhua Shen

   In Proc. of the IEEE International Conf. on Computer Vision, 2025

   Bib PDF

   @inproceedings{zhang2025pomato,
     title = {POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction},
     author = {Zhang, Songyan and Ge, Yongtao and Tian, Jinyuan and Xu, Guangkai and Lv, Chen and Chen, Hao and Shen, Chunhua},
     booktitle = {Proc. of the IEEE International Conf. on Computer Vision},
     year = {2025}
   }

2. 

   3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models

   Yongtao Ge, Wenjia Wang, Yongfan Chen, Hao Chen, and Chunhua Shen

   In IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2025

   Bib PDF Code

   @inproceedings{ge2024humanwild,
     title = {3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models},
     booktitle = {IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI)},
     author = {Ge, Yongtao and Wang, Wenjia and Chen, Yongfan and Chen, Hao and Shen, Chunhua},
     year = {2025}
   }

3. 

   What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

   Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, and Chunhua Shen

   In Proc. of the IEEE International Conf. on Learning Representations, 2025

   Bib PDF

   @inproceedings{xu2024genpercept,
     title = {What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?},
     author = {Xu, Guangkai and Ge, Yongtao and Liu, Mingyu and Fan, Chengxiang and Xie, Kangyang and Zhao, Zhiyue and Chen, Hao and Shen, Chunhua},
     booktitle = {Proc. of the IEEE International Conf. on Learning Representations},
     year = {2025}
   }

2024

1. 

   GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models

   Yongtao Ge, Guangkai Xu, Zhiyue Zhao, Zheng Huang, Libo Sun, Yanlong Sun, Hao Chen, and Chunhua Shen

   arXiv preprint arXiv:2406.12671, 2024

   Bib Code

   @article{ge2024geobench,
     title = {GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models},
     author = {Ge, Yongtao and Xu, Guangkai and Zhao, Zhiyue and Huang, Zheng and Sun, Libo and Sun, Yanlong and Chen, Hao and Shen, Chunhua},
     journal = {arXiv preprint arXiv:2406.12671},
     booktitle = {arXiv.org},
     year = {2024}
   }

2023

1. 

   Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

   Wenjia Wang, Yongtao Ge, Haiyi Mei, Zhongang Cai, Qingping Sun, Yanjun Wang, Chunhua Shen, Lei Yang, and Komura Taku

   In Proc. of the IEEE International Conf. on Computer Vision (ICCV Oral), 2023

   Bib PDF Code

   @inproceedings{wang2023zolly,
     title = {Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction},
     booktitle = {Proc. of the IEEE International Conf. on Computer Vision (ICCV Oral)},
     stars = {<a href="https://github.com/WenjiaWang0312/Zolly">
               <img alt="GitHub Repo stars" style="vertical-align: top" 
               src="https://img.shields.io/github/stars/WenjiaWang0312/Zolly?style=social">
             </a>},
     author = {Wang, Wenjia and Ge, Yongtao and Mei, Haiyi and Cai, Zhongang and Sun, Qingping and Wang, Yanjun and Shen, Chunhua and Yang, Lei and Taku, Komura},
     year = {2023}
   }

2. 

   Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations

   Yongtao Ge^*, Qiang Zhou^*, Xinlong Wang, Chunhua Shen, Zhibin Wang, and Hao Li

   In AAAI Conference on Artificial Intelligence (AAAI), 2023

   Bib PDF Code

   @inproceedings{ge2023point,
     title = {Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations},
     author = {Ge, Yongtao and Zhou, Qiang and Wang, Xinlong and Shen, Chunhua and Wang, Zhibin and Li, Hao},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2023}
   }

2022

1. 

   Poseur: Direct Human Pose Regression with Transformers

   Weian Mao^*, Yongtao Ge^*, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, and Anton van den Hengel

   In Proc. of the European Conf. on Computer Vision (ECCV), 2022

   Bib PDF Supp Code

   @inproceedings{mao2022poseur,
     title = {Poseur: Direct Human Pose Regression with Transformers},
     booktitle = {Proc. of the European Conf. on Computer Vision (ECCV)},
     stars = {
           <a href="https://github.com/aim-uofa/Poseur">
             <img alt="GitHub Repo stars" 
               style="vertical-align: top"
               src="https://img.shields.io/github/stars/aim-uofa/Poseur?style=social">
           </a>},
     author = {Mao, Weian and Ge, Yongtao and Shen, Chunhua and Tian, Zhi and Wang, Xinlong and Wang, Zhibin and Hengel, Anton van den},
     year = {2022}
   }