Introduces the TUB dataset of 1320 real turbid underwater images and PCD metric showing strong correlation with instance segmentation performance where standard metrics fail.
Deep Underwater Image Enhancement
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
In an underwater scene, wavelength-dependent light absorption and scattering degrade the visibility of images, causing low contrast and distorted color casts. To address this problem, we propose a convolutional neural network based image enhancement model, i.e., UWCNN, which is trained efficiently using a synthetic underwater image database. Unlike the existing works that require the parameters of underwater imaging model estimation or impose inflexible frameworks applicable only for specific scenes, our model directly reconstructs the clear latent underwater image by leveraging on an automatic end-to-end and data-driven training mechanism. Compliant with underwater imaging models and optical properties of underwater scenes, we first synthesize ten different marine image databases. Then, we separately train multiple UWCNN models for each underwater image formation type. Experimental results on real-world and synthetic underwater images demonstrate that the presented method generalizes well on different underwater scenes and outperforms the existing methods both qualitatively and quantitatively. Besides, we conduct an ablation study to demonstrate the effect of each component in our network.
representative citing papers
JWCDN embeds a simplified underwater image formation model into a GAN with multi-scale dense encoder-decoder and edge-preserving modules to jointly compensate wavelength attenuation and dehaze images, trained via a novel synthesis method simulating different water types.
A comprehensive survey of deep learning-based underwater image enhancement with systematic experimental comparison of algorithms on multiple datasets.
citing papers explorer
-
Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images
JWCDN embeds a simplified underwater image formation model into a GAN with multi-scale dense encoder-decoder and edge-preserving modules to jointly compensate wavelength attenuation and dehaze images, trained via a novel synthesis method simulating different water types.
-
Diving Deeper into Underwater Image Enhancement: A Survey
A comprehensive survey of deep learning-based underwater image enhancement with systematic experimental comparison of algorithms on multiple datasets.