Visual Intelligence Lab (VILab)

What We Do

Building physically grounded, human-centered computer vision for robust recognition, reconstruction, and generation in the wild

The Visual Intelligence Lab (VILab), led by Feng Liu, PhD at Drexel University’s School of Computer and Information Sciences, develops computer vision and machine learning methods for understanding, recognizing, and generating human appearance and motion. Our work spans 3D human reconstruction and digitization, multimodal biometrics (face, gait, and whole-body), and controllable generative AI, with an emphasis on robustness, trustworthiness, and physical plausibility. We collaborate across vision, graphics, biomechanics, and applied domains to translate research into real-world impact in areas such as health, safety, and human-centered AI. 

Research Faculty & PhD Students

  • Feng Liu, PhD, professor 
  • Yuyang Ji, PhD student
  • Yixuan Shen, PhD student

View a complete list of researchers on the VILab website.

Recent Publications

  • Su, Y., Shi, Y., Liu, F., & Liu, X. (2025). "HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID." In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2025).
  • Kim, M., Ye, D., Su, Y., Liu, F., & Liu, X. (2025). "SapiensID: Foundation for Human Recognition." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025).
  • Liu, F., & Liu, X. (2023). "Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects." IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • Dang, H., Liu, F., Stehouwer, J., Liu, X., & Jain, A. K. (2020). "On the Detection of Digital Face Manipulation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020).
  • Li, T., Liu, F., & Krajcik, J. (2023). "Automatically Assess Elementary Students’ Hand-Drawn Scientific Models Using Deep Learning." In Proceedings of the 17th International Conference of the Learning Sciences (ICLS 2023).

View a complete list of publications on the VILab website.

Visit the VILab website for more information