Underwater Light Field Retention : Neural Rendering for Underwater Imaging

  title={Underwater Light Field Retention : Neural Rendering for Underwater Imaging},
  author={Tian Ye and Sixiang Chen and Yunzhuo Liu and Erkang Chen and Yi Ye and Yuche Li},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Tian YeSixiang Chen Yuche Li
  • Published 21 March 2022
  • Computer Science
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Underwater Image Rendering aims to generate a true-to-life underwater image from a given clean one, which could be applied to various practical applications such as underwater image enhancement, camera filter, and virtual gaming. We explore two less-touched but challenging problems in underwater image rendering, namely, i) how to render diverse underwater scenes by a single neural network? ii) how to adaptively learn the underwater light fields from natural exemplars, i,e., realistic underwater… 

WaterNeRF: Neural Radiance Fields for Underwater Scenes

—Underwater imaging is a critical task performed by marine robots for a wide range of applications including aquaculture, marine infrastructure inspection, and environ- mental monitoring. However,



Deep Underwater Image Enhancement

A convolutional neural network based image enhancement model, i.e., UWCNN, which is trained efficiently using a synthetic underwater image database is proposed, which directly reconstructs the clear latent underwater image by leveraging on an automatic end-to-end and data-driven training mechanism.

Benchmarking Underwater Image Enhancement and Restoration, and Beyond

A new large-scale benchmark that contains ground-truth images and synthetic underwater images of the same scene, called synthetic underwater image dataset (SUID), constructed on the basis of the underwater image formation model (IFM) and characteristics of underwater optical propagation, possessing solid reliability and feasibility.

A Novel Underwater Image Synthesis Method Based on a Pixel-Level Self-Supervised Training Strategy

An underwater image synthesis method is proposed, which can directly convert the natural light image into the synthetic underwater image end-to-end, and a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images.

UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing

An unsupervised generative adversarial network (GAN) is proposed for generating realistic underwater images (color distortion and haze effect) from in-air image and depth map pairs based on improved underwater imaging model and U-Net, which is adopted for color restoration and dehazing.

An Underwater Image Enhancement Benchmark Dataset and Beyond

This paper constructs an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images and proposes an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs).

RUIG: Realistic Underwater Image Generation Towards Restoration

A novel method for generating synthetic underwater images considering revised image formation model is presented and used to train a conditional generative adversarial network (CGAN) towards restoration of degraded underwater images.

WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images

This letter reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color

Fast Underwater Image Enhancement for Improved Visual Perception

The proposed conditional generative adversarial network-based model is suitable for real-time preprocessing in the autonomy pipeline by visually-guided underwater robots and provides improved performances of standard models for underwater object detection, human pose estimation, and saliency prediction.

Shallow-UWnet : Compressed Model for Underwater Image Enhancement

This paper proposes a shallow neural network architecture, Shallow-UWnet which maintains performance and has fewer parameters than the state-of-art models, and demonstrates the generalization of the model by benchmarking its performance on a combination of synthetic and real-world datasets.