UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916658755403776 |
|---|---|
| author | Mandal, Debabrata Chattopadhyay, Soumitri Tong, Guansen Chakravarthula, Praneeth |
| author_facet | Mandal, Debabrata Chattopadhyay, Soumitri Tong, Guansen Chakravarthula, Praneeth |
| contents | Image restoration is essential for enhancing degraded images across computer vision tasks. However, most existing methods address only a single type of degradation (e.g., blur, noise, or haze) at a time, limiting their real-world applicability where multiple degradations often occur simultaneously. In this paper, we propose UniCoRN, a unified image restoration approach capable of handling multiple degradation types simultaneously using a multi-head diffusion model. Specifically, we uncover the potential of low-level visual cues extracted from images in guiding a controllable diffusion model for real-world image restoration and we design a multi-head control network adaptable via a mixture-of-experts strategy. We train our model without any prior assumption of specific degradations, through a smartly designed curriculum learning recipe. Additionally, we also introduce MetaRestore, a metalens imaging benchmark containing images with multiple degradations and artifacts. Extensive evaluations on several challenging datasets, including our benchmark, demonstrate that our method achieves significant performance gains and can robustly restore images with severe degradations. Project page: https://codejaeger.github.io/unicorn-gh |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations Mandal, Debabrata Chattopadhyay, Soumitri Tong, Guansen Chakravarthula, Praneeth Computer Vision and Pattern Recognition Image restoration is essential for enhancing degraded images across computer vision tasks. However, most existing methods address only a single type of degradation (e.g., blur, noise, or haze) at a time, limiting their real-world applicability where multiple degradations often occur simultaneously. In this paper, we propose UniCoRN, a unified image restoration approach capable of handling multiple degradation types simultaneously using a multi-head diffusion model. Specifically, we uncover the potential of low-level visual cues extracted from images in guiding a controllable diffusion model for real-world image restoration and we design a multi-head control network adaptable via a mixture-of-experts strategy. We train our model without any prior assumption of specific degradations, through a smartly designed curriculum learning recipe. Additionally, we also introduce MetaRestore, a metalens imaging benchmark containing images with multiple degradations and artifacts. Extensive evaluations on several challenging datasets, including our benchmark, demonstrate that our method achieves significant performance gains and can robustly restore images with severe degradations. Project page: https://codejaeger.github.io/unicorn-gh |
| title | UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15868 |