avatar

Aymen Mir

I am a Ph.D. student at the University of Tübingen and the Max Planck Institute for Informatics, where I am advised by Gerard Pons-Moll. I work on the capture and synthesis of realistic virtual humans — reconstructing human motion from images and wearable sensors, animating photorealistic avatars in novel 3D scenes, and generating human behaviour conditioned on 3D scenes and language.

I have interned at Snap Research in New York and at Huawei Noah's Ark Lab in London. Before my Ph.D., I obtained a Master's degree in Computer Science from Saarland University, Germany. My work was shortlisted for the Best Paper Award at CVPR 2021.

News

  • [Nov. 2025] I spent a wonderful summer interning at Snap Research in New York City.
  • [Oct. 2025] Honoured to be recognized as a Top Reviewer at NeurIPS 2025.
  • [Jun. 2024] I joined Huawei Noah’s Ark Lab in London as a research intern.
  • [Jun. 2024] We organized the Compositional 3D Vision Workshop at CVPR 2024.
  • [Mar. 2024] Our paper Generating Continual Human Motion in Diverse 3D Scenes was presented at 3DV 2024 in Davos.
  • [Feb. 2024] Website online!

Publications

  1. @article{mir2026ahoy,
      title   = {AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors},
      author  = {Mir, Aymen and Guler, Riza Alp and Tang, Xiangjun and Wonka, Peter and Pons-Moll, Gerard},
      journal = {arXiv preprint arXiv:2603.17975},
      year    = {2026}
    }
    
  2. @article{mir2026animated,
      title   = {Animated 3DGS Avatars in Diverse Scenes with Consistent Lighting and Shadows},
      author  = {Mir, Aymen and Guler, Riza Alp and Wang, Jian and Pons-Moll, Gerard and Zhou, Bing},
      journal = {arXiv preprint arXiv:2601.01660},
      year    = {2026}
    }
    
  3. @article{mir2025aha,
      title   = {AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting},
      author  = {Mir, Aymen and Wang, Jian and Guler, Riza Alp and Guo, Chuan and Pons-Moll, Gerard and Zhou, Bing},
      journal = {arXiv preprint arXiv:2511.09827},
      year    = {2025}
    }
    
  4. @article{khan2025fishnetpp,
      title   = {FishNet++: Analyzing the Capabilities of Multimodal Large Language Models in Marine Biology},
      author  = {Khan, Faizan Farooq and Radwan, Yousef and Abdelrahman, Eslam and Felemban, Abdulwahab and Mir, Aymen and Michiels, Nico K. and Temple, Andrew J. and Berumen, Michael L. and Elhoseiny, Mohamed},
      journal = {arXiv preprint arXiv:2509.25564},
      year    = {2025}
    }
    
  5. International Conference on 3D Vision (3DV), 2024.
    @inproceedings{mir2024continual,
      title     = {Generating Continual Human Motion in Diverse 3D Scenes},
      author    = {Mir, Aymen and Puig, Xavier and Kanazawa, Angjoo and Pons-Moll, Gerard},
      booktitle = {International Conference on 3D Vision (3DV)},
      pages     = {903--913},
      year      = {2024}
    }
    
  6. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    @inproceedings{guzov2021hps,
      title     = {Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-Localization in Large Scenes from Body-Mounted Sensors},
      author    = {Guzov, Vladimir and Mir, Aymen and Sattler, Torsten and Pons-Moll, Gerard},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      year      = {2021}
    }
    
  7. Advances in Neural Information Processing Systems (NeurIPS), 2020.
    @inproceedings{chibane2020ndf,
      title     = {Neural Unsigned Distance Fields for Implicit Function Learning},
      author    = {Chibane, Julian and Mir, Aymen and Pons-Moll, Gerard},
      booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
      year      = {2020}
    }
    
  8. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
    @inproceedings{mir2020pix2surf,
      title     = {Learning to Transfer Texture from Clothing Images to 3D Humans},
      author    = {Mir, Aymen and Alldieck, Thiemo and Pons-Moll, Gerard},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      year      = {2020}
    }
    

Talks

  • Jan. 2024 - CAIR Vision group at KAUST.
  • Aug. 2023 - Amazon Research, Tübingen.
Copied email to clipboard!