Papers
11
Total Citations
2,745
H-Index
8
About
Vincent Lepetit is a prominent computer vision researcher whose work has significantly advanced the fields of 3D object detection, pose estimation, and visual tracking. His most celebrated contribution, "Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes" (2013), has garnered over 1,190 citations, establishing him as a leading authority on recognizing and localizing objects that lack distinctive surface textures — a notoriously difficult challenge in real-world robotics and augmented reality applications. His comprehensive survey on monocular model-based 3D tracking of rigid objects, accumulating over 1,000 citations across versions, remains a foundational reference for researchers entering the field. Lepetit's work on view-based mapping further demonstrates his breadth, contributing to autonomous robotic navigation through stereo vision systems. More recently, his zero-shot, CAD-free approach to 6DoF tracking (PIZZA, 2022) reflects his forward-thinking push toward practical systems that require no prior object knowledge. Spanning two decades, Lepetit's research consistently bridges theoretical rigor and real-world applicability, making lasting contributions to augmented reality, robotic manipulation, and visual SLAM that continue to shape contemporary computer vision research.
Research Focus
Key Achievements
Top Papers
- 1
- 2Monocular Model-Based 3D Tracking of Rigid Objects: A Survey531 citations · 2005
- 3Monocular Model-Based 3D Tracking of Rigid Objects: A Survey469 citations · 2005
- 4
- 5View-based Maps224 citations · 2010
- 6View-based maps33 citations · 2009
- 7PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking19 citations · 2022
- 8
- 9ALCN: Adaptive Local Contrast Normalization8 citations · 2020
- 10Multi-Finger Grasping Like Humans4 citations · 2022