SOURCE-LINKED INTELLIGENCE

ImIR: Image-Instruction Tuning for All-in-One Image Restoration

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one model. A recent and effective recipe adapts a large pretrained image-editing model to restoration using a small low-rank adapter with a text prompt. We replace that prompt with an instruction derived from the degraded image itself. The image reaches the editor through two paths: its structure comes from the model's VAE, and its semantic instruction comes from a lightweight token mapper that shifts the degraded image's vision-language embedding toward the embedding a clean ima

Read original source ↗ Open in workspace

recordType

paper

region

Global