Abdulellah Abualshour



A master's student at King Abdullah University of Science and Technology majoring in Computer Science. Interested in computer vision, deep learning, and data science. I am proficient in Python, Java, SQL and deep learning technologies such as PyTorch, Tensorflow, and Keras.



  • [2019-12-13] Officially completed my master's degree course requirements. Started working on my master's thesis with Prof. Bernard Ghanem.
  • [2019-11-15] Submitted 1 paper to the Conference on Computer Vision and Pattern Recognition (CVPR 2020).
  • [2019-10-15] Submitted 1 paper to IEEE TPAMI journal, Special Issue on Graphs in Vision and Pattern Analysis.
  • [2019-09-02] Joined the Image and Video Understanding Lab at KAUST. Working on my master's thesis supervised by Prof. Bernard Ghanem.
  • [2019-08-08] Finished my internship with Saudi Aramco. Built a data warehouse for company data and designed an analytical dashboard.
  • [2019-06-16] Started my internship with Saudi Aramco as a Data Analytics Intern in the Project System Support Division - Systems Information Unit.
  • [2018-12-03] Elected Vice President of the KGSP Alumni Association for the 2019 academic year.
  • [2018-11-23] Joined the KGSP Alumni Association as a board member for the 2019 academic year.
  • [2018-08-15] Started my master's degree program at KAUST, majoring in Computer Science. Research topic: deep learning and computer vision.
  • [2018-08-04] Finished the research internship at KAUST. Implemented the NIvsCG paper using Keras as a deep learning framework.
  • [2018-05-19] Started a research internship in deep learning as part of Dr. Peter Wonka's group at the Visual Computing Center at KAUST.
  • [2018-05-13] Graduated with a B.S. degree in Computer Science from Rutgers, The State University of New Jersey.
  • [2017-11-12] Attended ACM/IEEE Supercomputing Conference (SC17) in Denver, CO, USA as an exhibitor (KAUST's Team).
  • [2017-07-27] Finished the research internship at KAUST. Project: Manual and Automatic Image Rectification.
  • [2017-05-20] Started a research internship in computer vision as part of Dr. Peter Wonka's group at the Visual Computing Center at KAUST.
  • [2017-04-06] Attended IEEE Big Data Service Conference in San Francisco, CA, USA.
  • [2016-08-24] Finished the internship at UT Austin. Project: Drone Calibration and Ground-station Implementation.
  • [2016-06-02] Started a software engineering internship at UT Austin's Department of Aerospace Engineering. Supervised by Ufuk Topcu.
  • [2015-01-29] Awarded a premier honor membership at the National Society of Collegiate Scholars (NSCS).
  • Selected Projects

    PU-GCN: Point Cloud Upsampling using GCNs

    In this paper, we propose 3 novel point upsampling modules: Multi-branch GCN, Clone GCN, and NodeShuffle. Our modules use Graph Convolutional Networks (GCNs) to better encode local point information. Our upsampling modules are versatile and can be incorporated into any point cloud upsampling pipeline. We show how our 3 modules consistently improve state-of-the-art methods in all point upsampling metrics. We also propose a new multi-scale point feature extractor.

    DeepGCNs: Making GCNs Go as Deep as CNNs

    This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of deep GCNs with as many as 112 layers experimentally across various datasets and tasks. Specifically, we achieve state-of-the-art performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs.

    Trash Material Classification via Deep Learning

    A good convolutional model can help create useful application for sorting trash material without the need of human contact with recycling equipment. In my experiments, I experiment with several methods and convolutional networks, including different optimization techniques and different network architectures in order to find the best and most accurate convolutional models for the trash material classification.

    Batch Gradient Descent, Stochastic Gradient Descent and Maximum Likelihood Estimation using Python

    Regression is an interesting technique of estimating the values among variables. In this experiment, I implement and test three algorithms of regression using the gaussian function as a basis function to fit random noisy data I generate that represent the cosine function.

    Analysis and Estimation of Influence of Authors and Papers in Computer Science

    Estimating the influence of authors and papers in the research field is an interesting problem. In this project, we mainly use a huge dataset to rank authors and papers and analyze their influence in the computer science research field using a graph building approach. Our methodology includes building a network graph that connects the research papers.

    Informed and Uniformed Search Analysis of the 8-Puzzle Problem

    Solving the 8-Puzzle is an interesting problem that requires an algorithmic approach in order to be done efficiently. We explore different approaches of solving the 8-Puzzle problem. The two main algorithms considered are BFS and A* search. Our work includes theoretical analysis of these algorithms in addition to experimentation with different heuristics in the A* algorithm.



    Research interests include deep learning, machine learning, data science, computer vision and computer graphics.


    Skilled in programming languages and technologies such as Python, C/C++, Java, Go, Matlab, SQL, SSIS, SSMS, Keras and PyTorch.

    Image Processing

    Experienced in different image processing techniques related to computer vision and computer graphics.

    Data Analytics

    Interested in data analysis and uncovering intriguing petterns in big data.


    A team player and collaborator in the research field.


    A mentor, a volunteer and an aspiring educator.

    Want to Get in Touch?

    Contact me