Google Scholar  /  CV

William J. Beksi

I am an Assistant Professor in the Department of Computer Science and Engineering at the University of Texas at Arlington. I'm also the founder and director of the Robotic Vision Laboratory. My research focuses on robotics, computer vision, and cyber-physical systems. In particular, I am interested in developing algorithms that enable machines to learn from their interactions with the physical world and autonomously acquire skills necessary to execute complex tasks.

Prospective students: If you are a current student at UT Arlington then please fill out this form. Otherwise, please apply directly to the PhD program and mention my name in your application.

Email: william.beksi at
Office: Engineering Research Building 523, 500 UTA Blvd, Arlington, TX 76019



A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds

M.S. Arshad and W.J. Beksi
International Conference on 3D Vision (3DV) 2020
PDF  •   BibTeX

Probabilistic Object Detection via Deep Ensembles

Z. Lyu, N. Gutierrez, A. Rajguru and W.J. Beksi
Beyond mAP: Reassessing the Evaluation of Object Detectors
European Conference on Computer Vision (ECCV) Workshop 2020


Thermal Image Super-Resolution Challenge - PBVS 2020

R.E. Rivadeneira, A.D. Sappa, B.X. Vintimilla, L. Guo, J. Hou, A. Merhi, P. Behjati, A.H. Patel, V. Chudasama, K. Prajapati, K.P. Upla, R. Ramachandra, K. Raja, C. Busch, F. Almasri, O. Debeir, S. Nathan, P. Kansal, N. Gutierrez, B. Mojra and W.J. Beksi
16th IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020

PDF  •   BibTeX  •   URL

Camera-Based Adaptive Trajectory Guidance via Neural Networks

A. Rajguru, C. Collander and W.J. Beksi
International Conference on Mechatronics and Robotics Engineering (ICMRE) 2020
Best Presentation Award  •   PDF  •   BibTeX

A Topology-Based Descriptor for 3D Point Cloud Modeling: Theory and Experiments

W.J. Beksi and N. Papanikolopoulos
Image and Vision Computing, 2019
PDF  •   BibTeX