Felipe Gomez Marulanda

Papers

Total Citations

H-Index

About

Felipe Gomez Marulanda is a researcher whose work lies at the intersection of 3D computer vision and deep learning, with a particular focus on point-cloud processing for robotics and sensor technologies. His most notable contribution is the development of IPC-Net (Inter-Point Convolutional Networks), introduced in his 2018 paper, which proposes a novel deep learning architecture for 3D point-cloud segmentation. Unlike traditional methods that struggle with the unstructured nature of point-clouds, IPC-Net leverages inter-point convolutional layers to capture local geometric features more effectively, advancing the accuracy of segmentation and classification in 3D spaces. This work, which has garnered 4 citations, addresses the growing demand for robust algorithms driven by the proliferation of 3D sensors in robotics and autonomous systems. Marulanda’s research is particularly relevant for applications in scene understanding, object recognition, and navigation, where precise 3D analysis is critical. By tackling the challenge of processing irregular point-cloud data, he contributes to the broader goal of enabling machines to perceive and interact with complex three-dimensional environments, making his work a stepping stone for future innovations in spatial AI.