UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations
This addresses a practical limitation in computer vision where existing methods only handle single degradations, making it incremental by extending to multiple types.
The paper tackles the problem of image restoration for multiple simultaneous degradations (e.g., blur, noise, haze) in real-world scenarios, proposing UniCoRN, a unified approach that achieves significant performance gains on challenging datasets, including a new benchmark called MetaRestore.
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