Towards Realistic Underwater Dataset Generation and Color Restoration
This work addresses the challenge of realistic color restoration in underwater imaging for applications like marine research and robotics, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of poor performance of deep-learning color restoration methods on real underwater images due to synthetic training data limitations by using an image-to-image translation network to adapt synthetic data to real conditions, then training a CNN on this adapted dataset to achieve improved color restoration.
Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is backscattering due to suspended particles in water. Thus, most existing deep-learning based color restoration methods, which are trained on synthetic underwater datasets, do not perform well on real underwater data. This can be attributed to the fact that synthetic data cannot accurately represent real conditions. To address this issue, we use an image to image translation network to bridge the gap between the synthetic and real domains by translating images from synthetic underwater domain to real underwater domain. Using this multimodal domain adaptation technique, we create a dataset that can capture a diverse array of underwater conditions. We then train a simple but effective CNN based network on our domain adapted dataset to perform color restoration. Code and pre-trained models can be accessed at https://github.com/nehamjain10/TRUDGCR