Yongtao Ge | 葛涌涛

I am a Ph.D. candidate in Computer Science, working in AIML, the University of Adelaide, with Prof. Chunhua Shen. Before that, I received the M. Eng degree from Southeast University and B. Eng degree from Nanjing University of Science and Technology.

My research interest mainly lies in the intersection of computer vision, computer graphics and machine learning, including 4D scene perception, reconstruction, and generation. I also work on human-centered digitization.

As a final year Ph.D. student, I am looking for industry positions or Post-doc opportunities. Please feel free to reach out to yongtao.ge@adelaide.edu.au if you have suitable positions and find me might be a fit.


News

Jan 23, 2025 GenPercept is accepted by ICLR 2025. 🎉
Jun 19, 2024 Release GeoBench, a monocular geometry benchmark for analyzing SOTA monocular geometry estimation models. 🎉
Mar 29, 2024 Release HumanWild, feel free to try our Huggingface Demo. 🎉
Jul 18, 2023 Zolly is accepted by ICCV 2023, selected as oral (top 1.8%). :sparkles:
Mar 27, 2023 Release Release HumanWild, focusing on perspective-distorted 3D human pose and shape estimation. :sparkles:

Publications

  1. geobench_logo.png
    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
  2. humanwild.gif
    3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models
    Yongtao GeWenjia Wang, Yongfan Chen, Hao Chen, and Chunhua Shen
    In arXiv.org, 2024
  3. genpercept_pipeline.png
    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
  4. zolly.png
    Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
    Wenjia WangYongtao Ge, Haiyi Mei, Zhongang Cai, Qingping Sun, Yanjun Wang, Chunhua ShenLei Yang, and Komura Taku
    In Proc. of the IEEE International Conf. on Computer Vision (ICCV Oral), 2023
  5. poseur_arch.jpg
    Poseur: Direct Human Pose Regression with Transformers
    In Proc. of the European Conf. on Computer Vision (ECCV), 2022
  6. point_teaching_arch.jpg
    Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations
    In AAAI Conference on Artificial Intelligence (AAAI), 2023