Papers
1
Total Citations
33
H-Index
1
About
Di Wang is an emerging researcher specializing in underwater image processing, computer vision, and marine robotics. His work addresses one of the most challenging problems in aquatic imaging: enhancing the quality of degraded underwater images to support real-world applications in marine engineering and autonomous underwater systems. His most notable contribution, "Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement" (2022), has garnered 33 citations and represents a significant methodological advance in the field. By developing a semantic-aware framework that intelligently fuses texture and structural features, Wang's approach tackles critical limitations that have long plagued the discipline — namely, the scarcity of reliable training datasets and the inconsistencies introduced by manually crafted ground truth images. This work improves the robustness of enhancement models when applied to previously unseen underwater scenarios, directly enabling more reliable high-level visual perception for aquatic robots and remote sensing platforms. Wang's research sits at a productive intersection of deep learning and domain-specific image restoration, and his early citation impact suggests a growing influence on how the computer vision community approaches the unique optical challenges of underwater environments.
Research Focus
Key Achievements
Top Papers
- 1