ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912132415619072 |
|---|---|
| author | Hu, Yuyang Peng, Albert Gan, Weijie Kamilov, Ulugbek S. |
| author_facet | Hu, Yuyang Peng, Albert Gan, Weijie Kamilov, Ulugbek S. |
| contents | Diffusion bridges (DB) have emerged as a promising alternative to diffusion models for imaging inverse problems, achieving faster sampling by directly bridging low- and high-quality image distributions. While incorporating measurement consistency has been shown to improve performance, existing DB methods fail to maintain this consistency in blind inverse problems, where the forward model is unknown. To address this limitation, we introduce ADOBI (Adaptive Diffusion Bridge for Inverse Problems), a novel framework that adaptively calibrates the unknown forward model to enforce measurement consistency throughout sampling iterations. Our adaptation strategy allows ADOBI to achieve high-quality parallel magnetic resonance imaging (PMRI) reconstruction in only 5-10 steps. Our numerical results show that ADOBI consistently delivers state-of-the-art performance, and further advances the Pareto frontier for the perception-distortion trade-off. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction Hu, Yuyang Peng, Albert Gan, Weijie Kamilov, Ulugbek S. Image and Video Processing Medical Physics Diffusion bridges (DB) have emerged as a promising alternative to diffusion models for imaging inverse problems, achieving faster sampling by directly bridging low- and high-quality image distributions. While incorporating measurement consistency has been shown to improve performance, existing DB methods fail to maintain this consistency in blind inverse problems, where the forward model is unknown. To address this limitation, we introduce ADOBI (Adaptive Diffusion Bridge for Inverse Problems), a novel framework that adaptively calibrates the unknown forward model to enforce measurement consistency throughout sampling iterations. Our adaptation strategy allows ADOBI to achieve high-quality parallel magnetic resonance imaging (PMRI) reconstruction in only 5-10 steps. Our numerical results show that ADOBI consistently delivers state-of-the-art performance, and further advances the Pareto frontier for the perception-distortion trade-off. |
| title | ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction |
| topic | Image and Video Processing Medical Physics |
| url | https://arxiv.org/abs/2411.16535 |