Faheem Ullah

About

Faheem Ullah is a researcher advancing the field of computer vision, with a focused expertise in 6D object pose estimation for robotic manipulation. His work addresses the critical challenge of enabling robots to accurately perceive and interact with objects in real-world environments, particularly those that are occluded or lack distinguishing textures. Ullah’s major contributions include the development of robust, end-to-end convolutional neural networks that achieve real-time performance. His 2023 paper, "6D object pose estimation based on dense convolutional object center voting with improved accuracy and efficiency," has garnered 5 citations for its novel approach to enhancing both precision and computational speed. Building on this, his 2022 work introduced a distance regularization voting loss function to further refine pose estimation from single RGB images, earning 4 citations. These innovations are pivotal for applications in automation and robotics, where reliable object handling is essential. Ullah’s research demonstrates a clear trajectory toward making 6D pose estimation more practical and robust, marking him as a promising contributor to intelligent systems and human-robot interaction.

Research Focus

Key Achievements

Top Papers

1. 1
   6D object pose estimation based on dense convolutional object center voting with improved accuracy and efficiency

   5 citations · 2023
2. 2
   A Robust Convolutional Neural Network for 6D Object Pose Estimation from RGB Image with Distance Regularization Voting Loss

   4 citations · 2022

Key Collaborators

Contact & Links