Wei Qin Chuah

Wei Qin Chuah is a Lecturer at the School of Engineering at RMIT University, Australia, specializing in computer vision and machine learning. His research focuses on developing robust and generalizable models for various computer vision applications, particularly in the domains of stereo matching, depth estimation, and autonomous vehicle systems.

Dr. Chuah's research interests span several key areas with particular emphasis on domain generalization and domain adaptation techniques that enable models trained on synthetic data to perform well on real-world applications. He has made significant contributions to stereo matching and depth estimation systems, developing methods to improve long-range perception for autonomous vehicles. His work on Neural Radiance Fields (NeRF) addresses challenges in learning from corrupted or uncurated image collections. Additionally, he has explored applications of computer vision in diverse domains including industrial inspection, veterinary assistance systems, and traffic management around construction sites.

Analysis of Dr. Chuah's publication trends reveals a consistent focus on addressing the challenge of synthetic-to-real domain shift, developing innovative methods like Information-Theoretic Shortcut Avoidance (ITSA) to prevent models from learning spurious correlations in synthetic training data. His recent work extends to keypoint estimation for industrial applications using micro-CT imaging and transfer learning, as well as developing artifact-free Neural Radiance Fields from uncurated image collections.

Dr. Chuah is currently supervising research projects including Learning Robust and Generalisable Models for Computer Vision Using Animation, indicating his ongoing commitment to training the next generation of computer vision researchers. His collaborative work spans multiple institutions, with frequent co-authorship patterns suggesting strong research partnerships with colleagues including Tennakoon R, Hoseinnezhad R, and Bab-Hadiashar A. His research bridges theoretical advances in machine learning with practical applications in autonomous systems, industrial automation, and healthcare.