Manu Tom
Papers
1
Total Citations
4
H-Index
1
About
Manu Tom is a researcher whose work lies at the intersection of computer vision, 3D scene understanding, and semantic segmentation. His key contributions focus on developing algorithms that enable machines to parse and interpret complex, real-world objects, particularly in the domain of modular furniture. In his notable 2017 paper, "3D Semantic Segmentation of Modular Furniture Using rjMCMC," Tom introduced a novel approach that uses reversible jump Markov Chain Monte Carlo (rjMCMC) to identify and label the structural components of furniture—such as doors, drawers, and shelves—even when their number and spatial arrangement are unknown. This work addresses a critical challenge in 3D perception: the automatic decomposition of composite objects into meaningful parts. While his citation count is still growing, Tom’s research is foundational for applications in robotics, augmented reality, and automated interior design, where understanding object structure is essential. His innovative use of probabilistic models for part-based segmentation marks him as a promising contributor to the field of 3D semantic understanding.
Research Focus
Key Achievements
Top Papers
- 13D Semantic Segmentation of Modular Furniture Using rjMCMC4 citations · 2017