U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911442588925952 |
|---|---|
| author | Varshney, Ayush Bouman, Katherine L. Feng, Berthy T. |
| author_facet | Varshney, Ayush Bouman, Katherine L. Feng, Berthy T. |
| contents | Ill-posed imaging inverse problems remain challenging due to the ambiguity in mapping degraded observations to clean images. Diffusion-based generative priors have recently shown promise, but typically rely on computationally intensive iterative sampling or per-instance optimization. Amortized variational inference frameworks address this inefficiency by learning a direct mapping from measurements to posteriors, enabling fast posterior sampling without requiring the optimization of a new posterior for every new set of measurements. However, they still struggle to reconstruct fine details and complex textures. To address this, we extend the amortized framework by injecting spatially adaptive perturbations to measurements during training, guided by uncertainty estimates, to emphasize learning in the most uncertain regions. Experiments on deblurring and super-resolution demonstrate that our method achieves superior or competitive performance to previous diffusion-based approaches, delivering more realistic reconstructions without the computational cost of iterative refinement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11704 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction Varshney, Ayush Bouman, Katherine L. Feng, Berthy T. Image and Video Processing Computer Vision and Pattern Recognition Ill-posed imaging inverse problems remain challenging due to the ambiguity in mapping degraded observations to clean images. Diffusion-based generative priors have recently shown promise, but typically rely on computationally intensive iterative sampling or per-instance optimization. Amortized variational inference frameworks address this inefficiency by learning a direct mapping from measurements to posteriors, enabling fast posterior sampling without requiring the optimization of a new posterior for every new set of measurements. However, they still struggle to reconstruct fine details and complex textures. To address this, we extend the amortized framework by injecting spatially adaptive perturbations to measurements during training, guided by uncertainty estimates, to emphasize learning in the most uncertain regions. Experiments on deblurring and super-resolution demonstrate that our method achieves superior or competitive performance to previous diffusion-based approaches, delivering more realistic reconstructions without the computational cost of iterative refinement. |
| title | U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.11704 |