Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks

TL;DR

This paper systematically evaluates Nano Banana 2, a general-purpose image editing model, for image restoration, highlighting its strengths in perceptual quality and generalization, while noting fidelity and controllability challenges.

Contribution

It provides a comprehensive assessment of Nano Banana 2's performance on image restoration, emphasizing prompt design importance and identifying gaps between perceptual quality and fidelity.

Findings

Nano Banana 2 achieves competitive performance in image restoration.

Concise prompts with explicit constraints improve results.

The model shows strong generalization but has issues with fidelity and consistency.

Abstract

Recent advances in generative AI raise the question of whether general-purpose image editing models can serve as unified solutions for image restoration. We conduct a systematic evaluation of Nano Banana 2 across diverse scenes and degradations. Our results show that prompt design is critical, with concise prompts and explicit fidelity constraints achieving a better balance between reconstruction and perceptual quality. Nano Banana 2 achieves competitive full-reference performance and is consistently preferred in user studies, while showing strong generalization in challenging scenarios. However, we observe a gap between perceptual quality and restoration fidelity, as the model tends to produce visually rich results with over-enhanced details and inconsistencies. This issue is not well captured by existing IQA metrics or user studies. Overall, general-purpose models show promise as unified IR solvers from a perceptual perspective, but require improved controllability and fidelity-aware evaluation. Further comparisons and detailed analyses are available in our project repository: https://github.com/yxyuanxiao/NanoBanana2TestOnIR.