Diffusion-Enhanced Underwater Debris Detection via Improved YOLOv12n Framework

Detecting underwater debris is important for monitoring the marine environment but remains challenging due to poor image quality, visual noise, object occlusions, and diverse debris appearances in underwater scenes. This study proposes UDD-YOLO, a novel detection framework that, for the first time, applies a diffusion-based model to underwater image enhancement, introducing a new paradigm for improving perceptual quality in marine vision tasks. Specifically, the proposed framework integrates three key components: (1) a Cold Diffusion module that acts as a pre-processing stage to restore image clarity and contrast by reversing deterministic degradation such as blur and occlusion—without injecting stochastic noise—making it the first diffusion-based enhancement applied to underwater object detection; (2) an AMC2f feature extraction module that combines multi-scale separable convolutions and learnable normalization to improve representation for targets with complex morphology and scale variation; and (3) a Unified-IoU (UIoU) loss function designed to dynamically balance localization learning between high- and low-quality predictions, thereby reducing errors caused by occlusion or boundary ambiguity. Extensive experiments are conducted on the public underwater plastic pollution detection dataset, which includes 15 categories of underwater debris. The proposed method achieves a mAP50 of 81.8%, with 87.3% precision and 75.1% recall, surpassing eleven advanced detection models such as Faster R-CNN, RT-DETR-L, YOLOv8n, and YOLOv12n. Ablation studies verify the function of every module. These findings show that diffusion-driven enhancement, when coupled with feature extraction and localization optimization, offers a promising direction for accurate, robust underwater perception, opening new opportunities for environmental monitoring and autonomous marine systems.