Marlon Marcon

Universidade Tecnológica Federal do Paraná

Papers

Total Citations

H-Index

About

Marlon Marcon is a researcher whose work sits at the intersection of computer vision, 3D geometry, and self-supervised learning. His primary research focus is on developing algorithms that enable machines to autonomously understand and interact with three-dimensional surfaces—a critical capability for applications in robotics, augmented reality, and autonomous navigation. Marcon’s most notable contribution is his 2020 paper, "Learning to Orient Surfaces by Self-supervised Spherical CNNs," which tackles the fundamental challenge of defining and reliably finding a canonical orientation for 3D surfaces. Rather than relying on handcrafted geometric cues, Marcon pioneered a self-supervised approach using spherical convolutional neural networks, allowing models to learn robust orientation features directly from data. This work, which has garnered 9 citations, represents a significant departure from traditional, designer-driven methods and opens new pathways for more adaptive and generalizable 3D perception systems. Marcon’s research is particularly impactful for students and researchers interested in the intersection of deep learning and geometric reasoning, offering a fresh perspective on how machines can learn to perceive the world in three dimensions without extensive human annotation.