DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation

📅 2025-10-12
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the challenge of modeling cross-domain non-uniform stylistic variations in underwater image synthesis—caused by optical phenomena such as color attenuation and turbidity—this paper proposes a style-content disentangled generative framework. Methodologically, it introduces K-means clustering for adaptive style-domain partitioning, employs a dual-branch encoder to separately extract disentangled style and content latent representations, and utilizes Adaptive Instance Normalization (AdaIN) for fine-grained style-feature fusion. The key contribution lies in the first integration of clustering-guided domain partitioning with explicit style-content disentanglement, significantly enhancing generalization across diverse underwater environments. Quantitative evaluation demonstrates state-of-the-art synthesis fidelity: SSIM = 0.9012, PSNR = 32.51 dB, and FID = 13.37.

Technology Category

Application Category

📝 Abstract
In this paper, we propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards photorealistic underwater image synthesis. The quality of synthetic underwater images is challenged by optical due to phenomena such as color attenuation and turbidity. These phenomena are represented by distinct stylistic variations across different waterbodies, such as changes in tint and haze. While generative models are well-suited to capture complex patterns, they often lack the ability to model the non-uniform conditions of diverse underwater environments. To address these challenges, we employ K-means clustering to partition a dataset into style-specific domains. We use separate encoders to get latent spaces for style and content; we further integrate these latent representations via Adaptive Instance Normalization (AdaIN) and decode the result to produce the final synthetic image. The model is trained independently on each style cluster to preserve domain-specific characteristics. Our framework demonstrates state-of-the-art performance, obtaining a Structural Similarity Index (SSIM) of 0.9012, an average Peak Signal-to-Noise Ratio (PSNR) of 32.5118 dB, and a Frechet Inception Distance (FID) of 13.3728.
Problem

Research questions and friction points this paper is trying to address.

Generating photorealistic underwater images with style-content disentanglement
Addressing color attenuation and turbidity in underwater image synthesis
Modeling non-uniform stylistic variations across different waterbodies
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses K-means clustering for style-specific domain partitioning
Employs separate encoders for disentangling style and content
Integrates latent representations via Adaptive Instance Normalization
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
S
Sneha Varur
KLE Technological University, Hubballi, Karnataka, India
A
Anirudh R Hanchinamani
KLE Technological University, Hubballi, Karnataka, India
T
Tarun S Bagewadi
KLE Technological University, Hubballi, Karnataka, India
U
Uma Mudenagudi
KLE Technological University, Hubballi, Karnataka, India
C
Chaitra D Desai
KLE Technological University, Hubballi, Karnataka, India
S
Sujata C
KLE Technological University, Hubballi, Karnataka, India
P
Padmashree Desai
KLE Technological University, Hubballi, Karnataka, India
S
Sumit Meharwade
KLE Technological University, Hubballi, Karnataka, India