3 papers
cs.CV2025
DPF-Net: Physical Imaging Model Embedded Data-Driven Underwater Image Enhancement
Han Mei, Kunqian Li, Shuaixin Liu +2
Due to the complex interplay of light absorption and scattering in the underwater environment, underwater images experience significant degradation. This research presents a two-st…
cs.CV2025
Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding
Chengzhi Ma, Kunqian Li, Shuaixin Liu +1
Indiscernible marine object counting encounters numerous challenges, including limited visibility in underwater scenes, mutual occlusion and overlap among objects, and the dynamic…
cs.CV2024
WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation
Yilin Ding, Kunqian Li, Han Mei +2
Depth information serves as a crucial prerequisite for various visual tasks, whether on land or underwater. Recently, self-supervised methods have achieved remarkable performance o…