A systematic review and analysis of deep learning-based underwater object detection

Aiming at the face photos of film and television animation, this paper proposes a new fast three-dimensional (3D) face modelling algorithm. First of all, based on the LBF algorithm, this paper prop...

/pdf/fast-modelling-algorithm-for-realistic-three-dimensional-bacuxausds.pdf

Fast Modelling Algorithm for Realistic Three-Dimensional Human Face for Film and Television Animation

Underwater enhancement based on a self-learning strategy and attention mechanism for high-intensity regions

This paper presents a modified version of the underwater dark channel prior algorithm for subaquatic image restoration based on Global Atmospheric Light Estimation for Underwater Image Restoration called as GALEIR. The proposed method uses the concept of underwater dark channel prior and attempts to increase the accuracy in atmospheric light estimation. Our methodology reduces the chances of inaccurate estimation of global atmospheric light by applying statistical mode operation on 1% of the brightest pixels chosen. Besides, a fast guided filter has been employed instead of complex Soft Matting for the transmission map refinement. The above-mentioned changes incorporated in the underwater dark channel prior algorithm increases the visual quality of the underwater image and consumes less computational time compared to iterative Soft Matting based restoration algorithms. We proffer the analysis of GALEIR by which its limitations and applicability are revealed. GALEIR has been evaluated on Underwater Colour Image Quality Evaluator (UCIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Underwater Image Quality Metrics (UIQM), and time complexity. The proposed algorithm yields higher UCIQE and lower BRISQUE scores of about 1.231 and 23.86, respectively, performing better than the state-of-the-art techniques.

GALEIR: Global Atmospheric Light Estimation based Underwater Image Restoration

Underwater image enhancement has played an important role in marine resource monitoring and preservation. However, the visual quality of underwater images is degraded due to light attenuation, background noise and water types, which brings challenging problems to underwater image enhancement. Existing Convolutional Neural Network (CNN) based methods do not fully explore degradation issues in different underwater scenes and also ignore color corrected priors, which limit their generalization and representation ability. To address the above mentioned problems, we propose a new Degradation-aware and Color-Corrected Network (DCN). Since it is difficult to estimate the degradation information of underwater image, we use Contrastive Learning (CL) to learn accurate degradation representation from input underwater images via a new degradation encoder. Then, to make the enhancement process adapt to different underwater images with the help of learned degradation representation and a color corrected prior, the DCN is built based on the proposed Degradation-aware and Color-corrected Block (DCB) for enhancing underwater images, which contains a degradation-aware branch, a color-corrected branch and an Edge Sharpness Layer (ESL). The degradation-aware branch recovers the clear image with the help of the degradation representation, while the color-corrected branch based on the color corrected prior compensates for the loss of information in the red channel. Furthermore, the ESL based on the unsharp masking principle is proposed and inserted at the end of the DCB for preserving details and sharpening edges. Such a design enables the DCN enhance underwater images, correct colors and sharpen edges simultaneously. The experiments on both synthetic and real images demonstrate that our method achieves pleasing visual results and outperforms state-of-the-art methods by a large margin. • A Degradation-aware and Color-Corrected Network (DCN) which enhances underwater images with different degradation and color deviation is proposed. • The proposed DCN consists two new modules: a new Degradation-aware and Color-Corrected Block (DCB) and a new Edge Sharpness Layer (ESL). • The new DCB is based on degradation representation trained by contrastive learning and a color-corrected prior. • The new ESL is based on the unsharp masking principle. 

Sheezan Fayaz

Papers

Underwater image restoration: A state‐of‐the‐art review

Underwater object detection: architectures and algorithms – a comprehensive review

GALEIR: Global Atmospheric Light Estimation based Underwater Image Restoration

Efficient underwater image restoration utilizing modified dark channel prior