GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909548748472320 |
|---|---|
| author | Rajagopalan, Sudarshan Nair, Nithin Gopalakrishnan Paranjape, Jay N. Patel, Vishal M. |
| author_facet | Rajagopalan, Sudarshan Nair, Nithin Gopalakrishnan Paranjape, Jay N. Patel, Vishal M. |
| contents | Deep learning-based models for All-In-One Image Restoration (AIOR) have achieved significant advancements in recent years. However, their practical applicability is limited by poor generalization to samples outside the training distribution. This limitation arises primarily from insufficient diversity in degradation variations and scenes within existing datasets, resulting in inadequate representations of real-world scenarios. Additionally, capturing large-scale real-world paired data for degradations such as haze, low-light, and raindrops is often cumbersome and sometimes infeasible. In this paper, we leverage the generative capabilities of latent diffusion models to synthesize high-quality degraded images from their clean counterparts. Specifically, we introduce GenDeg, a degradation and intensity-aware conditional diffusion model capable of producing diverse degradation patterns on clean images. Using GenDeg, we synthesize over 550k samples across six degradation types: haze, rain, snow, motion blur, low-light, and raindrops. These generated samples are integrated with existing datasets to form the GenDS dataset, comprising over 750k samples. Our experiments reveal that image restoration models trained on the GenDS dataset exhibit significant improvements in out-of-distribution performance compared to those trained solely on existing datasets. Furthermore, we provide comprehensive analyses on implications of diffusion model-based synthetic degradations for AIOR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17687 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration Rajagopalan, Sudarshan Nair, Nithin Gopalakrishnan Paranjape, Jay N. Patel, Vishal M. Computer Vision and Pattern Recognition Deep learning-based models for All-In-One Image Restoration (AIOR) have achieved significant advancements in recent years. However, their practical applicability is limited by poor generalization to samples outside the training distribution. This limitation arises primarily from insufficient diversity in degradation variations and scenes within existing datasets, resulting in inadequate representations of real-world scenarios. Additionally, capturing large-scale real-world paired data for degradations such as haze, low-light, and raindrops is often cumbersome and sometimes infeasible. In this paper, we leverage the generative capabilities of latent diffusion models to synthesize high-quality degraded images from their clean counterparts. Specifically, we introduce GenDeg, a degradation and intensity-aware conditional diffusion model capable of producing diverse degradation patterns on clean images. Using GenDeg, we synthesize over 550k samples across six degradation types: haze, rain, snow, motion blur, low-light, and raindrops. These generated samples are integrated with existing datasets to form the GenDS dataset, comprising over 750k samples. Our experiments reveal that image restoration models trained on the GenDS dataset exhibit significant improvements in out-of-distribution performance compared to those trained solely on existing datasets. Furthermore, we provide comprehensive analyses on implications of diffusion model-based synthetic degradations for AIOR. |
| title | GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.17687 |