Hamid Suleman

Fraunhofer Institute for Integrated Circuits

Papers

Total Citations

H-Index

About

Hamid Suleman is a researcher whose work sits at the intersection of computer vision, deep learning, and efficient multimedia compression. His primary research focuses on developing intelligent, data-driven methods for processing and compressing visual data, with a particular emphasis on stereo imagery—a critical input for autonomous driving, robotics, and 3D-TV. His most notable contribution is the paper "RNNSC: Recurrent Neural Network-Based Stereo Compression Using Image and State Warping" (2022), which introduces an end-to-end trainable recurrent neural network architecture for compressing stereo image pairs. This work is pioneering in its use of recurrent networks to exploit temporal and inter-view redundancies, achieving efficient compression without sacrificing reconstruction quality. With 4 citations, this paper has already drawn attention from researchers working on neural compression and autonomous perception systems. Suleman’s approach stands out for its practical applicability, offering a scalable solution for bandwidth-constrained environments. His work sits at the exciting intersection of deep learning and real-world engineering, promising to make high-quality stereo vision more accessible for next-generation intelligent systems.