Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement

by   Di Wang, et al.

Underwater image enhancement has become an attractive topic as a significant technology in marine engineering and aquatic robotics. However, the limited number of datasets and imperfect hand-crafted ground truth weaken its robustness to unseen scenarios, and hamper the application to high-level vision tasks. To address the above limitations, we develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model, aiming to exploit its hierarchical feature representation as an auxiliary for the low-level underwater image enhancement. Specifically, we tend to characterize the shallow layer features as textures while the deep layer features as structures in the semantic-aware model, and propose a multi-path Contextual Feature Refinement Module (CFRM) to refine features in multiple scales and model the correlation between different features. In addition, a feature dominative network is devised to perform channel-wise modulation on the aggregated texture and structure features for the adaptation to different feature patterns of the enhancement network. Extensive experiments on benchmarks demonstrate that the proposed algorithm achieves more appealing results and outperforms state-of-the-art methods by large margins. We also apply the proposed algorithm to the underwater salient object detection task to reveal the favorable semantic-aware ability for high-level vision tasks. The code is available at STSC.


page 1

page 2

page 5

page 6


LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement

Underwater image enhancement is an important low-level computer vision t...

Real-world Underwater Enhancement: Challenging, Benchmark and Efficient Solutions

Underwater image enhancement is an important low-level vision task with ...

Underwater Image Enhancement Based on Structure-Texture Reconstruction

Aiming at the problems of color distortion, blur and excessive noise of ...

A Correction-Based Dynamic Enhancement Framework towards Underwater Detection

To assist underwater object detection for better performance, image enha...

RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement

Underwater images typically experience mixed degradations of brightness ...

ACNet: Mask-Aware Attention with Dynamic Context Enhancement for Robust Acne Detection

Computer-aided diagnosis has recently received attention for its advanta...

Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration

Underwater images, in general, suffer from low contrast and high color d...

Please sign up or login with your details

Forgot password? Click here to reset