Muhammad Usama Saleem

Muhammad Usama Saleem

Ph.D. Student

University of North Carolina at Charlotte

About me

I am currently a Ph.D. candidate in the Department of Computer Science at the University of North Carolina at Charlotte , working under the supervision of Dr. Pu Wang at the GENIUS Lab . My research focuses on advancing computer vision and generative AI, particularly in 3D Human Pose Estimation and Mesh Recovery. Moreover, I am interested in 3D Human Motion Generation driven by multi-modal inputs (e.g., text, music, or speech), with a focus on achieving controllable, high-quality synthesis for realistic and dynamically responsive motion generation in real-time interactive settings.

Before joining UNCC, I earned my Bachelor's degree in Computer Science from Lahore University of Management Sciences (LUMS) in August 2021. There, I worked with Dr. Fareed Zaffar and Dr. Agha Ali Raza at the Center for Speech and Language Technologies (CSaLT) .

If you have any research opportunities, please feel free to reach out at msaleem2@charlotte.edu .

Research Interests

My research interests lie in Computer Vision and Generative AI. Specifically, I focus on two interconnected pillars:

  • 3D Human Pose Estimation and Mesh Recovery
  • Multi-Modality Motion Synthesis

News

  • Dec 2024: One paper, “GenHMR: Generative Human Mesh Recovery” is accepted to AAAI 2025!
  • Dec 2024: A paper on “MMHMR: Generative Masked Modeling for Hand Mesh Recovery” is now available on arXiv.
  • Oct 2024: A paper on “ControlMM: Controllable Masked Motion Generation” is now available on arXiv.
  • Oct 2024: One paper, “BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos,” is accepted to WACV 2025!
  • July 2024: One paper, “BAMM: Bidirectional Autoregressive Motion Model,” is accepted to ECCV 2024!
  • June 2023: One paper, “Private Data Synthesis from Decentralized Non-IID Data,” is accepted to IJCNN 2023, presented in Queensland, Australia, and received a $5000 travel grant!
  • April 2023: Presented at the SIAM International Conference on Data Mining (SDM'23) Doctoral Forum and received the NSF $1400 travel grant.
  • July 2022: One paper, “Privacy Enhancement for Cloud-Based Few-Shot Learning,” is accepted to IJCNN 2022!
  • Jan 2022: One paper, “DP-Shield: Face Obfuscation with Differential Privacy,” is accepted to EDBT 2022!

Recent Publications

MMHMR: Generative Masked Modeling for Hand Mesh Recovery

Arxiv 2024

ControlMM: Controllable Masked Motion Generation

Arxiv 2024

GenHMR: Generative Human Mesh Recovery

AAAI 2025

BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos

WACV 2025

BAMM: Bidirectional Autoregressive Motion Model

ECCV 2024