The scarcity of paired data severely limits the performance and generalization of learning-based underwater image enhancement (UIE) methods. This challenge is particularly prominent in scenes with complex degradations. Semi-supervised learning has emerged as a promising solution by enabling the utilization of large-scale unlabeled data. However, its effectiveness is limited by the use of static, model-agnostic metrics for pseudo-label reliability assessment. To address this, we propose SEA-PACE, a novel semi-supervised framework that integrates model-aware uncertainty modeling and self-paced consistency learning to fully exploit unlabeled data for UIE. Specifically, we design a Model-Aware Reliability Estimator (MARE) that quantifies the uncertainty of the teacher model's predictions through Gaussian Process Regression in latent feature space. The resulting uncertainty is then transformed into reliability weights via a rank-based mapping. Additionally, we apply the Self-Paced Consistency Learning (SPCL) strategy that employs a loss-aware schedule to dynamically prioritize high-confidence pseudo-labels, gradually incorporating more challenging samples during training. Extensive experiments on several public UIE benchmarks demonstrate that SEA-PACE consistently surpasses state-of-the-art methods in both visual quality and generalization capability.

Light propagation in underwater scenes is significantly hindered by wavelength- and distance-dependent attenuation and scattering, leading to low contrast and severe color distortion in underwater images. Recent advancements in diffusion models have shown impressive performance in image restoration by learning data distribution prior knowledge (diffusion prior) from large amounts of paired data. However, due to the difficulties in collecting paired underwater images, the available data for underwater image enhancement is limited in both quality and quantity. This scarcity leads to a biased diffusion prior and suboptimal performance of diffusion models. To address this issue, we propose a novel method, termed SeaDiff, to learn underwater diffusion prior with wavelength- and distance-dependent degradation awareness. Specifically, we introduce a Prior Knowledge Mining Model (PKMM), which includes two key components: (1) the Physical Prior Embedding Module (PPEM) that simulates the underwater imaging process through a distance-dependent physical model and embeds physical prior by incorporating generalizable distance-aware cues from a large vision foundation model; and (2) the Color Prior Embedding Module (CPEM) that extracts wavelength-dependent color distribution prior from a log-chroma color space. Additionally, we propose a Degradation-Aware Diffusion Model (DADM) that seamlessly integrates degradation prior with diffusion prior and enhances the underwater images with high visual quality. Extensive experiments on popular UIE benchmarks and downstream tasks demonstrate that the proposed SeaDiff achieves state-of-the-art performance in terms of both visual quality and quantitative metrics. The code will be released at https://github.com/Henry-Bi/SeaDiff.

As a prerequisite step of scene text reading, scene text detection is known as a challenging task due to natural scene text diversity and variability. Most existing methods either adopt bottom-up sub-text component extraction or focus on top-down text contour regression. From a hybrid perspective, we explore hierarchical text instance-level and component-level representation for arbitrarily-shaped scene text detection. In this work, we propose a novel Hierarchical Graph Reasoning Network (HGR-Net), which consists of a Text Feature Extraction Network (TFEN) and a Text Relation Learner Network (TRLN). TFEN adaptively learns multi-grained text candidates based on shared convolutional feature maps, including instance-level text contours and component-level quadrangles. In TRLN, an inter-text graph is constructed to explore global contextual information with position-awareness between text instances, and an intra-text graph is designed to estimate geometric attributes for establishing component-level linkages. Next, we bridge the cross-feed interaction between instance-level and component-level, and it further achieves hierarchical relational reasoning by learning complementary graph embeddings across levels. Experiments conducted on three publicly available benchmarks SCUT-CTW1500, Total-Text, and ICDAR15 have demonstrated that HGR-Net achieves state-of-the-art performance on arbitrary orientation and arbitrary shape scene text detection.

Document object detection is a challenging task due to layout complexity and object diversity. Most of existing methods mainly focus on vision information, neglecting representative inherent spatial-related relationship among document objects. To capture structural information and contextual dependencies, we propose a novel document object detector based on spatial-related relation and vision (SRRV). It consists of three parts: vision feature extraction network, relation feature aggregation network and result refinement network. Vision feature extraction network enhances information propagation of hierarchical feature pyramid by adopting feature augmentation paths. Then, relation feature aggregation network combines graph construction module and graph learning module. Specifically, graph construction module calculates spatial information from geometric attributes of region proposals to encode relation information, while graph learning module stacks Graph Convolutional Network (GCN) layers to aggregate relation information at global scale. Both the vision and relation features are fed into result refinement network for feature fusion and relational reasoning. Experiments on the PubLayNet, POD and Article Regions datasets demonstrate that spatial relation information improves the performance with better accuracy and more precise bounding box prediction.