Lucas Ricardo Vieira Messias

Papers

Total Citations

H-Index

About

Lucas Ricardo Vieira Messias is a researcher at the intersection of computer vision, image restoration, and the robustness of autonomous perception systems. His work critically examines the vulnerabilities of state-of-the-art Convolutional Neural Networks (ConvNets) to real-world image distortions, such as exposure variations, noise, and compression artifacts. His 2019 study, with 16 citations, systematically assessed how these common manipulations can degrade the reliability of CNN-based image recognition, highlighting critical safety concerns for autonomous systems. Messias further extended this line of inquiry in his 2021 work on the robustness of robotic perception, earning 7 citations. His most cited paper, a 2020 study on CNN-based image restoration (25 citations), proposes methods to recover visual quality from degraded inputs, directly addressing the vulnerabilities he previously identified. By bridging the gap between image restoration and the safety of autonomous perception, Messias’s research provides foundational insights for building more resilient AI systems, making his contributions essential reading for students and engineers working on reliable computer vision for real-world deployment.