The quality of underwater imagery is inherently degraded by light absorption and scattering, a challenge that severely limits its application in critical domains such as marine robotics and archeology. While existing enhancement methods, including recent hybrid models, attempt to address this, they often struggle to restore fine-grained details without introducing visual artifacts. To overcome this limitation, this work introduces a novel hybrid U-Net-Transformer (UTR) architecture that synergizes local feature extraction with global context modeling. The core innovation is a Recurrent Multi-Scale Feature Modulation (R-MSFM) mechanism, which, unlike prior recurrent refinement techniques, employs a gated modulation strategy across multiple feature scales within the decoder to iteratively refine textural and structural details with high fidelity. This approach effectively preserves spatial information during upsampling. Extensive experiments demonstrate the superiority of the proposed method. On the EUVP dataset, UTR achieves a PSNR of 28.347 dB, a significant gain of +3.947 dB over the state-of-the-art UWFormer. Moreover, it attains a top-ranking UIQM score of 3.059 on the UIEB dataset, underscoring its robustness. The results confirm that UTR provides a computationally efficient and highly effective solution for underwater image enhancement.

Monocular depth estimation is widely used for navigation and scene understanding, yet deployment requires balancing accuracy with predictable runtime and compact models. Many recent lightweight designs pair depthwise separable convolutions with transformer components to boost accuracy, which typically introduces a more diverse operator set and can make realized throughput more dependent on the deployment backend in practice. Instead, we revisit recurrent refinement from a deployment-oriented perspective and introduce R-TAFM, purely convolutional framework that performs iterative depth refinement at a fixed working resolution with a parameter-shared decoder. We further derive a deployment-mode variant, R-TAFM-Fast, which is trained with recurrent supervision yet reduces inference to a single decoder pass, lowering latency on commodity GPU and on a Jetson-class embedded GPU. For self-supervised learning, we introduce an adaptive reprojection objective that jointly handles occlusions and independently moving objects without auxiliary tasks, and a neighborhood-consistent correction of auto-masked stationary pixels to prevent supervision collapse in homogeneous regions. Both quantitative benchmarks and qualitative assessments demonstrate that, with $$\approx $$ ≈ 3.2M parameters, R-TAFM achieves accuracy comparable to or exceeding recent lightweight state-of-the-art methods, using only standard convolutions.

Underwater object detection is challenged by scale variation, light attenuation, scattering, and non-uniform illumination, which weaken texture and boundary cues and increase background interference, particularly for small and distant objects. To address these issues, this study proposes a multi-dimensional collaborative enhancement framework. A Feature Enhancement Module (FEM) integrates local and contextual information through heterogeneous convolutional branches and residual learning. A Spatial-Attention-Based Spatial Pyramid Pooling (SPP_SA) module combines multi-scale pooling with spatial attention to suppress irrelevant background responses. A Soft Nearest-Neighbor Interpolation (SNI) module introduces response-scaled nearest-neighbor upsampling to regulate feature magnitude during resolution recovery and support cross-level fusion. Experiments on UTDAC2020, Brackish, and RUOD demonstrate consistent improvements under different underwater conditions. Compared with the YOLOv11 baseline, the proposed method improves ${\mathrm{mAP}}_{50:95}$ by 5.56%, 3.37%, and 0.81% on UTDAC2020, Brackish, and RUOD, respectively. These results support the effectiveness of the proposed framework for mixed-scale underwater object detection, including small-scale objects.