Implicit Image-to-Image Schrodinger Bridge for Image Restoration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916659303809024 |
|---|---|
| author | Wang, Yuang Yoon, Siyeop Jin, Pengfei Tivnan, Matthew Song, Sifan Chen, Zhennong Hu, Rui Zhang, Li Li, Quanzheng Chen, Zhiqiang Wu, Dufan |
| author_facet | Wang, Yuang Yoon, Siyeop Jin, Pengfei Tivnan, Matthew Song, Sifan Chen, Zhennong Hu, Rui Zhang, Li Li, Quanzheng Chen, Zhiqiang Wu, Dufan |
| contents | Diffusion-based models have demonstrated remarkable effectiveness in image restoration tasks; however, their iterative denoising process, which starts from Gaussian noise, often leads to slow inference speeds. The Image-to-Image Schrödinger Bridge (I$^2$SB) offers a promising alternative by initializing the generative process from corrupted images while leveraging training techniques from score-based diffusion models. In this paper, we introduce the Implicit Image-to-Image Schrödinger Bridge (I$^3$SB) to further accelerate the generative process of I$^2$SB. I$^3$SB restructures the generative process into a non-Markovian framework by incorporating the initial corrupted image at each generative step, effectively preserving and utilizing its information. To enable direct use of pretrained I$^2$SB models without additional training, we ensure consistency in marginal distributions. Extensive experiments across many image corruptions, including noise, low resolution, JPEG compression, and sparse sampling, and multiple image modalities, such as natural, human face, and medical images, demonstrate the acceleration benefits of I$^3$SB. Compared to I$^2$SB, I$^3$SB achieves the same perceptual quality with fewer generative steps, while maintaining or improving fidelity to the ground truth. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06069 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Implicit Image-to-Image Schrodinger Bridge for Image Restoration Wang, Yuang Yoon, Siyeop Jin, Pengfei Tivnan, Matthew Song, Sifan Chen, Zhennong Hu, Rui Zhang, Li Li, Quanzheng Chen, Zhiqiang Wu, Dufan Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Diffusion-based models have demonstrated remarkable effectiveness in image restoration tasks; however, their iterative denoising process, which starts from Gaussian noise, often leads to slow inference speeds. The Image-to-Image Schrödinger Bridge (I$^2$SB) offers a promising alternative by initializing the generative process from corrupted images while leveraging training techniques from score-based diffusion models. In this paper, we introduce the Implicit Image-to-Image Schrödinger Bridge (I$^3$SB) to further accelerate the generative process of I$^2$SB. I$^3$SB restructures the generative process into a non-Markovian framework by incorporating the initial corrupted image at each generative step, effectively preserving and utilizing its information. To enable direct use of pretrained I$^2$SB models without additional training, we ensure consistency in marginal distributions. Extensive experiments across many image corruptions, including noise, low resolution, JPEG compression, and sparse sampling, and multiple image modalities, such as natural, human face, and medical images, demonstrate the acceleration benefits of I$^3$SB. Compared to I$^2$SB, I$^3$SB achieves the same perceptual quality with fewer generative steps, while maintaining or improving fidelity to the ground truth. |
| title | Implicit Image-to-Image Schrodinger Bridge for Image Restoration |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.06069 |