DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914089639346176 |
|---|---|
| author | Varur, Sneha Hanchinamani, Anirudh R Bagewadi, Tarun S Mudenagudi, Uma Desai, Chaitra D C, Sujata Desai, Padmashree Meharwade, Sumit |
| author_facet | Varur, Sneha Hanchinamani, Anirudh R Bagewadi, Tarun S Mudenagudi, Uma Desai, Chaitra D C, Sujata Desai, Padmashree Meharwade, Sumit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10782 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation Varur, Sneha Hanchinamani, Anirudh R Bagewadi, Tarun S Mudenagudi, Uma Desai, Chaitra D C, Sujata Desai, Padmashree Meharwade, Sumit Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10782 |