Cunyue Lu

Papers

Total Citations

H-Index

About

Cunyue Lu is a leading researcher in underwater computer vision, specializing in deep learning-based image enhancement and restoration. His work addresses critical challenges in oceanic exploration, where degraded visual quality from light absorption and scattering hinders autonomous underwater robots. Lu’s most cited paper, "Underwater Image Enhancement based on Deep Learning and Image Formation Model" (2021, 51 citations), pioneers a fusion of physical image formation models with neural networks, significantly improving clarity and color fidelity in turbid environments. This breakthrough directly supports applications in geological surveying, resource extraction, and ecological monitoring. In "Progressive Attentional Learning for Underwater Image Super-Resolution" (2020, 9 citations), he introduced an attention-driven framework that progressively refines low-resolution underwater imagery, achieving state-of-the-art detail recovery. Lu’s contributions are foundational for advancing robotic perception in extreme aquatic conditions, with his methods widely adopted in marine research and industrial inspection. His work bridges the gap between physical optics and deep learning, enabling more reliable autonomous operations in challenging underwater environments.