Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914715867807744 |
|---|---|
| author | Tang, Haoyue Xie, Tian Feng, Aosong Wang, Hanyu Zhang, Chenyang Bai, Yang |
| author_facet | Tang, Haoyue Xie, Tian Feng, Aosong Wang, Hanyu Zhang, Chenyang Bai, Yang |
| contents | Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can leverage a pretrained diffusion generative model to solve a wide range of image inverse tasks without task specific model fine-tuning. To precisely estimate the guidance score function of the input image, we propose Diffusion Policy Gradient (DPG), a tractable computation method by viewing the intermediate noisy images as policies and the target image as the states selected by the policy. Experiments show that our method is robust to both Gaussian and Poisson noise degradation on multiple linear and non-linear inverse tasks, resulting into a higher image restoration quality on FFHQ, ImageNet and LSUN datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10585 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint Tang, Haoyue Xie, Tian Feng, Aosong Wang, Hanyu Zhang, Chenyang Bai, Yang Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can leverage a pretrained diffusion generative model to solve a wide range of image inverse tasks without task specific model fine-tuning. To precisely estimate the guidance score function of the input image, we propose Diffusion Policy Gradient (DPG), a tractable computation method by viewing the intermediate noisy images as policies and the target image as the states selected by the policy. Experiments show that our method is robust to both Gaussian and Poisson noise degradation on multiple linear and non-linear inverse tasks, resulting into a higher image restoration quality on FFHQ, ImageNet and LSUN datasets. |
| title | Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.10585 |