Expert Operational GANS: Towards Real-Color Underwater Image Restoration
Ozer Can Devecioglu, Serkan Kiranyaz, Mehmet Yamac, and Moncef Gabbouj

TL;DR
This paper introduces xOp-GAN, a multi-generator GAN model for underwater image restoration that outperforms single-regressor models by specializing generators for different quality ranges and selecting the best output during inference.
Contribution
The paper proposes xOp-GAN, the first GAN with multiple expert generators and a discriminator used during inference to improve underwater image restoration.
Findings
Achieves PSNR up to 25.16 dB on LSUI dataset
Surpasses all single-regressor models in performance
Reduces complexity compared to existing methods
Abstract
The wide range of deformation artifacts that arise from complex light propagation, scattering, and depth-dependent attenuation makes the underwater image restoration to remain a challenging problem. Like other single deep regressor networks, conventional GAN-based restoration methods struggle to perform well across this heterogeneous domain, since a single generator network is typically insufficient to capture the full range of visual degradations. In order to overcome this limitation, we propose xOp-GAN, a novel GAN model with several expert generator networks, each trained solely on a particular subset with a certain image quality. Thus, each generator can learn to maximize its restoration performance for a particular quality range. Once a xOp-GAN is trained, each generator can restore the input image and the best restored image can then be selected by the discriminator based on its…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Signal Denoising Methods · Image Enhancement Techniques · Underwater Acoustics Research
