Peter De Roovere
Papers
1
Total Citations
4
H-Index
1
About
Peter De Roovere is a researcher in computer vision and robotics, specializing in 6D object pose estimation—the critical task of determining an object’s exact position and orientation in three-dimensional space from a single image. His major contribution, the CenDerNet framework, introduces a novel approach that combines center and curvature representations with a render-and-compare strategy, enabling more accurate and robust pose estimation even under challenging conditions like occlusion or clutter. Though early in his career, his work has already garnered attention, with his most-cited paper accumulating 4 citations and establishing a foundation for future advancements in the field. De Roovere’s research bridges the gap between geometric deep learning and practical robotic applications, offering potential impacts on autonomous manipulation, augmented reality, and industrial automation. His innovative use of curvature cues represents a promising departure from traditional keypoint-based methods, marking him as an emerging voice in the quest for more reliable visual perception systems.
Research Focus
Key Achievements
Top Papers
- 1