Demetri Terzopoulos

About

Demetri Terzopoulos is a Distinguished Professor and Chancellor’s Professor of Computer Science at UCLA Samueli School of Engineering. His research interests include computer graphics, computer vision, medical image analysis, computer-aided design, and artificial life and intelligence. He holds a Ph.D. from the Massachusetts Institute of Technology and both a Master’s and Bachelor’s degree from McGill University. Throughout his career, he has received numerous awards and recognitions, including the IEEE Computer Pioneer Award, the Academy Award for Technical Achievement, and fellowships from prestigious organizations such as the IEEE, ACM, and the Royal Society of Canada. His contributions have significantly advanced the fields of computer graphics and artificial intelligence, establishing him as a leading figure in these areas.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Optometry
• Pediatrics
• Ophthalmology
• Medicine
• Computer vision
• Internal medicine

Selected publications

• Image Segmentation Using Deep Learning: A Survey

  arXiv (Cornell University) · 2021 · 143 citations

  Senior authorCorresponding

  Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among others, and numerous segmentation algorithms are found in the literature. Against this backdrop, the broad success of deep learning (DL) has prompted the development of new image segmentation approaches leveraging DL models. We provide a comprehensive review…

• Artificial intelligence-enabled screening for diabetic retinopathy: a real-world, multicenter and prospective study

  BMJ Open Diabetes Research & Care · 2020 · 103 citations

  INTRODUCTION: Early screening for diabetic retinopathy (DR) with an efficient and scalable method is highly needed to reduce blindness, due to the growing epidemic of diabetes. The aim of the study was to validate an artificial intelligence-enabled DR screening and to investigate the prevalence of DR in adult patients with diabetes in China. RESEARCH DESIGN AND METHODS: The study was prospectively conducted at 155 diabetes centers in China. A non-mydriatic, macula-centered fundus photograph per…

  DOI

• Wonderland: Navigating 3D Scenes From a Single Image

  2025-06-10 · 10 citations

  article

  How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time-consuming per-scene optimization, distorted geometry in occluded areas, and low visual quality in backgrounds. Our novel 3D scene reconstruction pipeline overcomes these limitations to tackle the aforesaid challenge. Specifically, we introduce a large-scale reconstruction model that leverages latents from a video diff…

  PublisherDOI

• Position Paper: Agent AI Towards a Holistic Intelligence

  arXiv (Cornell University) · 2024-02-28 · 9 citations

  preprintOpen access

  Recent advancements in large foundation models have remarkably enhanced our understanding of sensory information in open-world environments. In leveraging the power of foundation models, it is crucial for AI research to pivot away from excessive reductionism and toward an emphasis on systems that function as cohesive wholes. Specifically, we emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. The emerging field of Agent AI spans a wide…

  PublisherOA PDFDOI

• Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering

  The Journal of Machine Learning for Biomedical Imaging · 2025-03-14 · 8 citations

  articleOpen accessSenior author

  Large Vision-Language Models (LVLMs) have achieved significant success in recent years, and they have been extended to the medical domain. Although demonstrating satisfactory performance on medical Visual Question Answering (VQA) tasks, Medical LVLMs (MLVLMs) suffer from the hallucination problem, which makes them fail to diagnose complex pathologies. Moreover, they readily fail to learn minority pathologies due to imbalanced training data. We propose two prompting strategies for MLVLMs that red…

  PublisherOA PDFDOI

Recent grants

• ITR: Intelligent Deformable Models

  NSF · $696k · 2007–2009

• ITR: Intelligent Deformable Models

  NSF · $1.2M · 2003–2008

Frequent coauthors

• Gerhard Weikum

  1747 shared

• David Hutchison

  Lancaster University

  1747 shared

• Friedemann Mattern

  1747 shared

• Bernhard Steffen

  TU Dortmund University

  1747 shared

• Doug Tygar

  University of California, Berkeley

  1747 shared

• Oscar Nierstrasz

  1746 shared

• Moni Naor

  1745 shared

• C Pandu

  TU Dortmund University

  1742 shared

Education

• Ph.D., Computer Science

  University of California, Los Angeles

  1984

• M.S., Computer Science

  University of California, Los Angeles

  1981

• B.S., Computer Science

  National Technical University of Athens

  1977

Awards & honors

• Canadian Human-Computer Communications Society (CHCCS) Achie…
• Founding Member of the Hellenic Institute of Advanced Studie…
• Inaugural Fellow of the Asia-Pacific Artificial Intelligence…
• IETI Distinguished Fellow, 2020
• IEEE Computer Pioneer Award, 2020

Similar researchers at University of California, Los Angeles

• Wei Wangh-91
• Eleazar Eskinh-83
• Stefano Soattoh-83