Towards Generating Realistic Underwater Images
This paper explores the use of contrastive learning and generative adversarial networks for generating realistic underwater images from synthetic images with uniform lighting. We investigate the performance of image translation models for generating realistic underwater images using the VAROS dataset. Two key evaluation metrics, Fr\'echet Inception Distance (FID) and Structural Similarity Index Measure (SSIM), provide insights into the trade-offs between perceptual quality and structural preservation. For paired image translation, pix2pix achieves the best FID scores due to its paired supervision and PatchGAN discriminator, while the autoencoder model attains the highest SSIM, suggesting better structural fidelity despite producing blurrier outputs. Among unpaired methods, CycleGAN achieves a competitive FID score by leveraging cycle-consistency loss, whereas CUT, which replaces cycle-consistency with contrastive learning, attains higher SSIM, indicating improved spatial similarity retention. Notably, incorporating depth information into CUT results in the lowest overall FID score, demonstrating that depth cues enhance realism. However, the slight decrease in SSIM suggests that depth-aware learning may introduce structural variations.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningSSIMTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models
This paper tackles the problem of generating representations of underwater 3D terrain. Off-the-shelf generative models, trained on Internet-scale data but not on specialized underwater images, exhibit downgraded realism,…
3D geometry3DGSWaterGen: Decoupling Scene and Medium in Underwater Image Generation
Underwater computer vision tasks, such as detection, restoration, and segmentation, are limited by the scarcity of large-scale and diverse training data. We introduce WaterGen, a method for generating large-scale, realis…
Semantic SegmentationScene GenerationImage GenerationUWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing
In real-world underwater environment, exploration of seabed resources, underwater archaeology, and underwater fishing rely on a variety of sensors, vision sensor is the most important one due to its high information cont…
Generative Adversarial NetworkGPUWaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images
This paper 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 correction of monocular un…
Generative Adversarial NetworkAtlantis: Enabling Underwater Depth Estimation with Stable Diffusion
Monocular depth estimation has experienced significant progress on terrestrial images in recent years, largely due to deep learning advancements. However, it remains inadequate for underwater scenes, primarily because of…
Depth EstimationImage RestorationMonocular Depth EstimationStyle Transfer+1