Demetri Terzopoulos

About

Demetri Terzopoulos is a pioneering researcher whose work spans computer vision, artificial life, robotics, and physically-based simulation. Best known for foundational contributions to active vision and autonomous agents, Terzopoulos introduced the influential *animat vision* paradigm, which leverages artificial animals situated in simulated environments as a software-driven alternative to traditional hardware-based vision systems — a paper that has garnered over 112 citations. His survey on deep learning-based image segmentation (143 citations) has become an essential reference for researchers tackling scene understanding, medical imaging, and augmented reality applications. Beyond vision, Terzopoulos has made significant strides in robotics and physical interaction, developing frameworks for inferring forces and human utilities from video (83 citations), and advancing deformable object manipulation through novel approaches like neural force manifolds and real-time DLO detection. His work on humanoid robot balance recovery and hybrid deliberative-reactive control architectures further demonstrates his broad commitment to intelligent autonomous systems. With contributions spanning nearly three decades — from real-time computer vision in 1995 to sim-to-real robotic manipulation in 2024 — Terzopoulos remains a deeply influential figure whose interdisciplinary research continues to shape how machines perceive, learn from, and physically interact with the world.

Research Focus

Key Achievements

Top Papers

1. 1
   Image Segmentation Using Deep Learning: A Survey

   143 citations · 2021
2. 2
   Animat vision: Active vision in artificial animals

   112 citations · 2002
3. 3
   Inferring Forces and Learning Human Utilities from Videos

   83 citations · 2016
4. 4
   Real-time computer vision

   55 citations · 1995
5. 5
   mBEST: Realtime Deformable Linear Object Detection Through Minimal Bending Energy Skeleton Pixel Traversals

   25 citations · 2023
6. 6
   The Cognitive Controller: A Hybrid, Deliberative/Reactive Control Architecture for Autonomous Robots

   19 citations · 2004
7. 7
   Intelligent perception and control for space robotics

   13 citations · 2007
8. 8
   Learning Neural Force Manifolds for Sim2Real Robotic Symmetrical Paper Folding

   11 citations · 2024
9. 9
   Learning Arm Motion Strategies for Balance Recovery of Humanoid Robots

   11 citations · 2010
10. 10
    Autonomous reactive control for simulated humanoids

    10 citations · 2004

Key Collaborators

Contact & Links