Arkadipta De
Papers
1
Total Citations
11
H-Index
1
About
Arkadipta De is a rising researcher at the forefront of 3D computer vision, with a primary focus on unsupervised domain adaptation (UDA) for point cloud data. His work tackles the critical challenge of bridging domain gaps caused by varying sensor types, noise patterns, and environmental conditions in real-world applications like robotics and scene understanding. In his most-cited paper, "Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation" (2024, 11 citations), De introduces a novel framework that harmonizes contrastive learning with optimal transport theory. This approach effectively aligns source and target domain features, enabling models to generalize without labeled target data—a breakthrough for autonomous systems operating in dynamic, unlabeled environments. By addressing the fundamental issue of domain shift in 3D data, De’s contributions are paving the way for more robust and adaptable perception systems. His work has already garnered attention for its innovative fusion of geometric and statistical methods, marking him as a promising voice in the field. With a focus on practical, scalable solutions, De is poised to influence the next generation of 3D deep learning research.
Research Focus
Key Achievements
Top Papers
- 1