Particle-Filtering-based Latent Diffusion for Inverse Problems
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_ | 1866913480257306624 |
|---|---|
| author | Nazemi, Amir Sepanj, Mohammad Hadi Pellegrino, Nicholas Czarnecki, Chris Fieguth, Paul |
| author_facet | Nazemi, Amir Sepanj, Mohammad Hadi Pellegrino, Nicholas Czarnecki, Chris Fieguth, Paul |
| contents | Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, instead drawing only a single sample from a Gaussian distribution from which to generate their solution. In this paper, we introduce a particle-filtering-based framework for a nonlinear exploration of the solution space in the initial stages of reverse SDE methods. Our proposed particle-filtering-based latent diffusion (PFLD) method and proposed problem formulation and framework can be applied to any diffusion-based solution for linear or nonlinear inverse problems. Our experimental results show that PFLD outperforms the SoTA solver PSLD on the FFHQ-1K and ImageNet-1K datasets on inverse problem tasks of super resolution, Gaussian debluring and inpainting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13868 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Particle-Filtering-based Latent Diffusion for Inverse Problems Nazemi, Amir Sepanj, Mohammad Hadi Pellegrino, Nicholas Czarnecki, Chris Fieguth, Paul Computer Vision and Pattern Recognition Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, instead drawing only a single sample from a Gaussian distribution from which to generate their solution. In this paper, we introduce a particle-filtering-based framework for a nonlinear exploration of the solution space in the initial stages of reverse SDE methods. Our proposed particle-filtering-based latent diffusion (PFLD) method and proposed problem formulation and framework can be applied to any diffusion-based solution for linear or nonlinear inverse problems. Our experimental results show that PFLD outperforms the SoTA solver PSLD on the FFHQ-1K and ImageNet-1K datasets on inverse problem tasks of super resolution, Gaussian debluring and inpainting. |
| title | Particle-Filtering-based Latent Diffusion for Inverse Problems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.13868 |