Marine Saliency Segmentation (MSS) plays a pivotal role in a wide range of vision-based marine exploration tasks. However, existing techniques often face the dilemma of imprecise boundaries due to the interference-rich nature of underwater environments, where suspended particles, low contrast, and color distortion hinder accurate segmentation. Although diffusion models have shown impressive performance in visual tasks, their potential to incorporate contextual semantics for enhancing feature learning of region-level salient objects remains underexplored, thereby hindering segmentation outcomes. Building on this insight, we propose DiffMSS, a novel marine saliency segmenter based on the diffusion model, which utilizes semantic knowledge distillation to guide the detection of marine salient objects. Specifically, we design the Word-level Semantic Saliency Extraction module that identifies salient terms at the word level from the captions by computing region-word similarity. These high-level semantic features are distilled into the Conditional Feature Learning Network to generate accurate and semantically informed diffusion conditions. The Object-Focused Conditional Diffusion module then leverages these conditions to iteratively generate fine-grained segmentation masks of marine instances, while a Consensus Deterministic Sampling scheme is further employed to suppress overconfident mis-segmentations and enhance structural fidelity. Extensive experiments demonstrate the superior performance of DiffMSS over state-of-the-art methods in both quantitative and qualitative evaluations. Our code and pre-trained models will be released on GitHub.

Underwater salient object detection (USOD) plays a pivotal role in various vision-based marine exploration tasks. However, existing USOD techniques face the dilemma of object mislocalization and imprecise boundaries due to the complex underwater environment. The quality degradation of raw underwater images (caused by selective absorption and medium scattering) makes it challenging to perform instance detection directly. One conceivable approach involves initially removing visual disturbances through underwater image enhancement (UIE), followed by saliency detection. However, this two-stage approach neglects the potential positive impact of the restoration procedure on saliency detection due to it executes in a cascade. Based on this insight, we propose a generalized prior-involved diffusion model, called WaterDiffusion for collaborative underwater saliency detection and visual restoration. Specifically, we first propose a revised self-attention joint diffusion, which embeds dynamic saliency masks into the diffusive network as latent features. By extending the underwater degradation prior into the multi-scale decoder, we innovatively exploit optical transmission maps to aid in localizing underwater salient objects. Then, we further design a gate-guided binary indicator to select either normalized or raw channels for improving feature generalization. Finally, the Half-quadratic Splitting is introduced into the unfolding sampling to refine saliency masks iteratively. Comprehensive experiments demonstrate the superior performance of WaterDiffusion over state-of-the-art methods in both quantitative and qualitative evaluations.

ABSTRACT Underwater images often suffer from visual degradation, affecting downstream tasks. While recent underwater image enhancement (UIE) techniques have made some advances benefiting from deep neural networks, challenges remain in restoring fine details and achieving computational efficiency. Inspired by the success of diffusion models in image generation, we propose the Underwater Laplacian‐Guided Diffusion Model (ULDM), which enhances image features layer‐by‐layer based on the hierarchical structure of the Laplacian pyramid transform to achieve both high‐quality and efficient UIE. The Laplacian pyramid decomposes the degraded image into high‐ and low‐frequency components, enabling the model to denoise the low‐frequency spectrum and address global image degradation, thereby reducing computational overhead. To efficiently enhance high‐frequency details, we introduce the Hierarchical Attention Weighted Module (HAWM) that leverages the strong pixel correlations in high‐frequency sub‐images at different levels, adjusting them layer‐by‐layer to better capture fine details. These high‐frequency sub‐images exhibit strong pixel correlation and consistent texture features across different layers, and their hierarchical pattern ensures effective detail restoration. Extensive experiments demonstrate that ULDM outperforms state‐of‐the‐art methods in both quantitative and qualitative evaluations.