Zifan Lin

Papers

Total Citations

H-Index

About

Zifan Lin is a rising researcher in computer vision and image processing, with a focused expertise in underwater image enhancement and reconstruction. His work addresses the critical challenges of degraded visual data in aquatic environments, where light absorption and scattering severely compromise image quality. Lin’s most influential contribution, “Semantic-guided diffusion for water-related image enhancement” (2025, 4 citations), introduces a novel diffusion-based framework that leverages semantic cues to restore clarity and color fidelity in underwater scenes—a significant step forward for autonomous underwater vehicles and marine monitoring. Complementing this, his paper “Depth-aware and continuous edge curves for large-view underwater image reconstruction” (2025, 2 citations) proposes a method that preserves structural integrity across wide-angle views, enabling more accurate 3D scene recovery. Though early in his career, Lin’s work has already garnered attention for its innovative integration of deep learning with physical priors of water optics. His achievements underscore a promising trajectory in advancing vision systems for challenging real-world conditions, with potential applications in oceanography, environmental science, and underwater robotics.